Comprehensive open-source toolbox for analysing Spatial Point Patterns. Focused mainly on two-dimensional point patterns, including multitype/marked points, in any spatial region. Also supports three-dimensional point patterns, space-time point patterns in any number of dimensions, point patterns on a linear network, and patterns of other geometrical objects. Supports spatial covariate data such as pixel images. Contains over 2000 functions for plotting spatial data, exploratory data analysis, model-fitting, simulation, spatial sampling, model diagnostics, and formal inference. Data types include point patterns, line segment patterns, spatial windows, pixel images, tessellations, and linear networks. Exploratory methods include quadrat counts, K-functions and their simulation envelopes, nearest neighbour distance and empty space statistics, Fry plots, pair correlation function, kernel smoothed intensity, relative risk estimation with cross-validated bandwidth selection, mark correlation functions, segregation indices, mark dependence diagnostics, and kernel estimates of covariate effects. Formal hypothesis tests of random pattern (chi-squared, Kolmogorov-Smirnov, Monte Carlo, Diggle-Cressie-Loosmore-Ford, Dao-Genton, two-stage Monte Carlo) and tests for covariate effects (Cox-Berman-Waller-Lawson, Kolmogorov-Smirnov, ANOVA) are also supported. Parametric models can be fitted to point pattern data using the functions ppm(), kppm(), slrm(), dppm() similar to glm(). Types of models include Poisson, Gibbs and Cox point processes, Neyman-Scott cluster processes, and determinantal point processes. Models may involve dependence on covariates, inter-point interaction, cluster formation and dependence on marks. Models are fitted by maximum likelihood, logistic regression, minimum contrast, and composite likelihood methods. A model can be fitted to a list of point patterns (replicated point pattern data) using the function mppm(). The model can include random effects and fixed effects depending on the experimental design, in addition to all the features listed above. Fitted point process models can be simulated, automatically. Formal hypothesis tests of a fitted model are supported (likelihood ratio test, analysis of deviance, Monte Carlo tests) along with basic tools for model selection (stepwise(), AIC()) and variable selection (sdr). Tools for validating the fitted model include simulation envelopes, residuals, residual plots and Q-Q plots, leverage and influence diagnostics, partial residuals, and added variable plots.

This repository holds a copy of the *current development version*
of the contributed R-package `spatstat`

.

This development version is more recent than the official *release*
of `spatstat`

on CRAN. Each official release of `spatstat`

has a
version number like `1.2-3`

while the development version has a
version number like `1.2-3.004`

. Official releases occur every 8 weeks
(the minimum time permitted by CRAN policies) while the development code
is updated almost every day.

The easiest way to install the development version of `spatstat`

from github is through the `devtools`

package:

require(devtools)install_github('spatstat/spatstat')

If you don't have `devtools`

installed you should first run

install.packages('devtools')

Users of `spatstat`

are encouraged to report bugs here
(press *issue* in the menu on the right to start a new bug report
or feature request).

Feel free to fork `spatstat`

, make changes to the code,
and ask us to include them in the package by making a github *pull request*.

However, this repository is only a copy of the development code, so your pull request may not be implemented until the next official release.

```
CHANGES IN spatstat VERSION 1.57-1
```

OVERVIEW

```
o Bug fixes.
o Version nickname: 'Cartoon Physics'
```

BUG FIXES

```
o multiplicity.default
Some entries of the result were incorrectly set to 1.
Fixed.
o anova.ppm
Crashed if adjust=TRUE and the models were fitted with use.gam=TRUE.
Fixed.
CHANGES IN spatstat VERSION 1.57-0
```

OVERVIEW

```
o We thank Corey Anderson, Ryan Arellano, Hadrien Commenges,
Ottmar Cronie, Tilman Davies, Maximilian Hesselbarth, Kassel Hingee,
Tomas Lazauskas, Marie-Colette van Lieshout, Rasmus Waagepetersen
and 'daitakahashi' for contributions.
o Cronie-van Lieshout bandwidth selection.
o Smoothing functions handle non-Gaussian kernels.
o Infinite smoothing bandwidths permitted.
o Positive confidence limits for rhohat.
o Improved bivariate interpolation.
o subset() method for line segment patterns.
o Important bug fixes in rthin and density.ppp
o Minor bug fixes and improvements.
o Version nickname: 'Zombie apocalypse'
```

NEW FUNCTIONS

```
o bw.CvL
Cronie-Van Lieshout bandwidth selection for density estimation.
[Contributed by Ottmar Cronie and Marie-Colette van Lieshout.]
o subset.psp
Method for 'subset' for line segment patterns.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o densityfun.ppp, Smoothfun.ppp, Smooth.ppp
These commands now handle non-Gaussian kernels.
o density.ppp, relrisk.ppp, Smooth.ppp, densityfun.ppp, Smoothfun.ppp
Argument 'sigma' can be infinite.
o interp.im
New argument 'bilinear' specifies the choice of interpolation rule.
o rhohat
Methods for rhohat have a new argument 'positiveCI'
specifying whether confidence limits should be positive.
o plot.colourmap
New argument 'increasing' specifies whether the colours are
displayed in order left-to-right/bottom-to-top.
Changed default behaviour for discrete colour maps when vertical=FALSE.
o split.ppx
Argument 'f' can be a logical vector.
o relrisk.ppp
If se=TRUE and at="pixels", the result belongs to class 'solist'.
o imcov, setcov, convolve.im
The name of the unit of length is preserved.
o density.ppp
Slightly accelerated for non-Gaussian kernels.
o bw.scott
The two bandwidth values in the result
now have names ('sigma.x' and 'sigma.y').
o pairdist.default
Now checks whether the data are valid 2-dimensional coordinates.
o pixellate.ppp
New argument 'savemap'
o rtemper
New argument 'track'.
Code runs slightly faster.
o eval.im, eval.linim
New argument 'warn'.
o Kres, Kcom, Gcom, psstG
If any of the calculated weights for the summary function
are infinite or NA, they are reset to zero, with a warning,
instead of a fatal error.
```

BUG FIXES

```
o rthin
If P was close to 1, the result was sometimes an empty point pattern
when it should have been identical to X.
[Spotted by Maximilian Hesselbarth.]
Fixed.
o density.ppp
Standard error calculations were incorrect
when sigma was a single numeric value.
The output was equal to 'sqrt(sigma)' times the correct answer.
Fixed.
o density.ppp
Result was incorrect for non-Gaussian kernels when
at="points" and leaveoneout=FALSE.
Fixed.
o density.ppp
Did not pass additional arguments "..." to a user-supplied
kernel function, in some cases.
Fixed.
o as.im.function, as.im.funxy
If the function values were factor values and the window was
not a rectangle, the result was an image with all pixel values NA.
[Spotted by Corey Anderson.]
Fixed.
o plot.funxy
If the function values were factor values and the window was
not a rectangle, the plot was empty.
[Spotted by Corey Anderson.]
Fixed.
o nnorient
Crashed if the border correction did not retain any data points.
[Spotted by Tomas Lazauskas.]
Fixed.
o linim
Crashed in some cases with a message about unitnames.
Fixed.
o density.lpp
Default value of 'dx' was sometimes incorrect.
Fixed.
o rMatClust, rThomas, rCauchy, rVarGamma
Issued a spurious warning about bandwidth selection
when saveLambda=TRUE.
Fixed.
o density.ppp
Issued a spurious warning about bandwidth selection
when 'kernel' was a user-supplied function.
Fixed.
o clusterfield.function
Issued a spurious warning about bandwidth selection.
Fixed.
```

o relrisk.ppp Issued a spurious warning if the argument 'case' or 'control' was given, for a bivariate point pattern. Fixed.

o superimpose.ppp If 'W' was a character string or function, the behaviour was not exactly as described in the help file. Fixed.

o plot.psp If the marks were factor values, the colour map was displayed upside down. Fixed.

o eval.fv If one of the 'fv' objects included ratio information (class 'rat') then this was erroneously retained, in some cases. Fixed.

o linearKcross Crashed (with a message about a missing value of 'correction') if there were no pairs of points to count. Fixed.

o envelope.lpp Crashed (randomly) when fix.n=TRUE and fix.marks=TRUE. Fixed.

```
CHANGES IN spatstat VERSION 1.56-1
```

OVERVIEW

```
o We thank Agustin Lobo for contributions.
o Improvements to infrastructure.
o Bug fixes.
o Version nickname: "Invisible Friend"
```

NEW FUNCTIONS

```
o as.im.expression
New method for 'as.im' for expressions.
o flipxy.tess
Method for 'flipxy' for tessellations.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o sdr
This is now a generic function, with a method for class 'ppp'.
o pointsOnLines
The result now has an attribute named "map"
which maps each point to its parent line segment.
o summary.lpp
Improved output.
o intersect.owin
Argument 'fatal' now defaults to FALSE.
o quadrature schemes (class "quad" and "logiquad")
Improved print and summary methods.
```

BUG FIXES

```
o cut.lpp
Crashed if the marks were a data frame or hyperframe.
Fixed.
o summary.lpp, print.summary.lpp
Output was garbled if the marks were a data frame or hyperframe.
Fixed.
o integral.linim
Crashed if the function had NA values.
Fixed.
o Tstat
Crashed if ratio=TRUE.
Fixed.
o intersect.owin
Ignored argument 'fatal' in some cases.
[Spotted by Agustin Lobo.]
Fixed.
o plot.tess
Crashed if do.col=TRUE and 'values' was a factor.
Fixed.
o pcf.ppp
Crashed if 'domain' was given and ratio=TRUE.
Fixed.
o "[<-.sparse3Darray"
Crashed if 'value' was one-dimensional
and the indices i, j, k specified a two-dimensional subset of x.
Fixed.
o plot.quad
Crashed if tiles=TRUE for a quadrature scheme
created by quadscheme(method="dirichlet", exact=TRUE).
Fixed.
o bugtable
Crashed if there were no bugs!
Fixed.
o sparse array code
An array bounds violation (segmentation fault) could occur.
Fixed.
o internal code
Numerous internal bugs have been fixed.
CHANGES IN spatstat VERSION 1.56-0
```

OVERVIEW

```
o We thank Sebastian Meyer and Suman Rakshit for contributions.
o Kernel estimate of intensity as a function(x,y)
o Extract discrete and continuous components of a measure.
o Improvements and extensions to leverage and influence code.
o Plot a line segment pattern using line widths.
o Find connected components of each tile in a tessellation.
o Geometrical operations on 'distfun' objects.
o Join vertices in a linear network.
o Distance map and contact distribution for rectangular structuring element.
o An infinite number of infinitesimal bugs has been detected and fixed.
o Version nickname: "Bondi Tram"
```

NEW FUNCTIONS

```
o densityfun, densityfun.ppp
Compute a kernel estimate of intensity of a point pattern
and return it as a function of spatial location.
o as.im.densityfun
Convert function(x,y) to a pixel image.
o measureDiscrete, measureContinuous
Extract the discrete and continuous components of a measure.
o connected.tess
Find connected components of each tile in a tessellation
and make a new tessellation composed of these pieces.
o dffit.ppm
Effect change diagnostic DFFIT for spatial point process models.
o shift.distfun, rotate.distfun, reflect.distfun, flipxy.distfun,
affine.distfun, scalardilate.distfun
Methods for geometrical operations on 'distfun' objects.
o rescale.distfun
Change the unit of length in a 'distfun' object.
o plot.indicfun
Plot method for indicator functions created by as.function.owin.
o Smooth.leverage.ppm, Smooth.influence.ppm
Smooth a leverage function or an influence measure.
o integral.leverage.ppm, integral.influence.ppm
Compute the integral of a leverage function or an influence measure.
o mean.leverage.ppm
Compute the mean value of a leverage function.
o rectdistmap
Distance map using rectangular metric.
o rectcontact
Contact distribution function using rectangular structuring element.
o joinVertices
Join specified vertices in a linear network.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o plot.psp
Segments can be plotted with widths proportional to their mark values.
New argument 'style'.
o msr
Infinite and NA values are now detected (if check=TRUE)
and are reset to zero, with a warning.
o leverage.ppm, influence.ppm, dfbetas.ppm
Faster computation in some cases.
o as.im.nnfun, as.im.smoothfun
New argument 'approx' chooses between a fast, approximate algorithm
and a slow, exact algorithm.
o cdf.test
More jittering is applied when jitter=TRUE.
Warnings about tied values should not occur any more.
o plot.im
Improved behaviour when all pixel values are NA.
o plot.tess
Now generates a separate plot panel for each column of marks,
if do.col=TRUE.
New argument 'multiplot'.
o pcfinhom
Now handles correction='good'
o solist
New argument '.NameBase'
o runifpointOnLines, rpoisppOnLines
New argument 'drop'
o plot.studpermutest
This existing function now has a help file.
o bdist.points
Accelerated, for polygonal windows (thanks to Sebastian Meyer).
o linnet
When argument 'edges' is specified, the code now checks whether
any edges are duplicated.
```

BUG FIXES

```
o kernel.moment
Result was incorrect for kernel="cosine" and kernel="optcosine".
Fixed.
o "[.msr"
Format was mangled if the subset contained exactly one quadrature point.
Fixed.
o tess
If a list of tiles was given, and the tiles were pixel images or masks,
their pixel resolutions were ignored, and reset to the default 128x128.
Fixed.
o plot.linim
Ignored argument 'legend' when style="colour".
[Spotted by Suman Rakshit.]
Fixed.
o leverage.ppm, influence.ppm, dfbetas.ppm
Crashed sometimes if the model was fitted by method="logi".
Fixed.
o Smooth.ppp
Crashed with some combinations of the arguments varcov and weights
when X had several columns of marks.
Fixed.
o plot.tess
Crashed sometimes when do.col=TRUE and values=NULL.
Fixed.
o dilation.ppp
Crashed if polygonal=FALSE.
o plot.tess
Ignored the marks of a tessellation defined by a pixel image.
Fixed.
o predict.ppm
Crashed when computing a confidence interval or prediction interval
if 'window' was a tessellation.
Fixed.
o tiles
names(tiles(x)) was not always identical to tilenames(x).
Fixed.
o model.images.lppm
Crashed in many cases.
Fixed.
o model.images.lppm
Names or dimnames were missing in some cases.
Fixed.
o nncross.ppp
Result had the wrong format if npoints(X) = 0 and length(what) = 1.
(Spotted by Sebastian Meyer).
Fixed.
o plot.colourmap
Crashed if the colourmap was defined on an interval of dates or times.
Fixed.
o StraussHard, leverage.ppm, influence.ppm, dfbetas.ppm
Leverage and influence calculations generated an error
when applied to models fitted with the StraussHard interaction.
Fixed.
o "[.ppp"
Crashed if there were several columns of marks,
some of which were factors, and drop=TRUE.
Fixed.
CHANGES IN spatstat VERSION 1.55-1
```

OVERVIEW

```
o We thank Jens Astrom, Ines Moncada, Mehdi Moradi and Nicholas Read
for contributions.
o More support for tessellations.
o Improved support for linear networks.
o Fixed longstanding bug in leverage and influence diagnostics.
o Minor improvements and bug fixes.
o Version nickname: "Gamble Responsibly"
```

NEW FUNCTIONS

```
o summary.ssf
Summary method for a spatially sampled function (class 'ssf').
o unstack.tess
Given a tessellation with multiple columns of marks,
take the columns one at a time, and return a list of tessellations,
each carrying only one of the original columns of marks.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o plot.tess
This plot method can now fill each tile with a different colour.
New arguments 'do.col', 'values', 'col' and 'ribargs'.
Old argument 'col' has been renamed 'border' for consistency.
o integral.linim, integral.linfun
Argument 'domain' can now be a tessellation.
o integral.ssf
Argument 'domain' can now be a tessellation.
o as.owin.default
Now accepts a structure with entries named 'xmin,ymin,xmax,ymax'
in any order. This handles objects of class 'bbox' in the 'sf' package.
o as.owin.default
Now detects objects of class "SpatialPolygons"
and issues a more helpful error message.
o pseudoR2.ppm, pseudoR2.lppm
The null model now includes any offset terms, by default.
[Suggested by Jens Astrom.]
New argument 'keepoffset'.
o closepairs.ppp
New argument 'periodic'
o fitted.ppm
New argument 'ignore.hardcore'.
o predict.ppm
New argument 'ignore.hardcore'.
o leverage.ppm, influence.ppm, dfbetas.ppm
Computation has been vastly accelerated for models with Geyer interaction
fitted using isotropic or translation edge corrections.
o leverage.ppm, influence.ppm, dfbetas.ppm
Virtually all models and edge corrections are now supported,
using a "brute force" algorithm. This can be slow in some cases.
o cdf.test
Monte Carlo test runs faster.
o summary.distfun, summary.funxy
Pixel resolution can now be controlled.
o persp.funxy
Improved z-axis label.
o plot.ppp
Improved placement of symbol legend when argument 'symap' is given.
o plot.msr
Changed the default rule for bandwidth for smoothing the density.
```

BUG FIXES

```
o nnmark, as.im.ssf
if marks(X) was a matrix rather than a data frame,
the results were completely incorrect (and had completely wrong format).
Fixed.
o predict.mppm
If the model included random effects, and if the library 'MASS' was not loaded,
the predictions were on the log scale (i.e. they were logarithms of the correct values).
[Spotted by Nicholas Read.]
Fixed.
o leverage.ppm, influence.ppm, dfbetas.ppm
Calculations were slightly incorrect for models with a hard core.
Fixed.
o leverage.ppm
The mean leverage value (shown as a contour line in plot.leverage.ppm)
was slightly incorrect for Gibbs models.
Fixed.
o Ops.msr
If the input data contained an auxiliary pixel image of
the density component of the measure (attribute "smoothdensity")
this image was not updated; it was copied to the output unchanged.
Plots of the resulting measure were incorrect, but calculations
with the measure were correct.
Fixed.
o integral.msr
If the result was a matrix, it was the transpose of the correct answer.
Fixed.
o "[.linim"
The result sometimes had the wrong class.
Fixed.
o "[.linnet"
In calculating L[W] where W is a window, the code ignored
segments of L that crossed W without having a vertex in W.
Fixed.
o nnmap
Crashed if W = NULL.
Fixed.
o density.lpp, nncross.lpp
Crashed sometimes with an obscure message about "z$which".
[Spotted by Ines Moncada.]
Fixed.
o as.im.distfun
Crashed, for the distfun of a point pattern, if approx=FALSE.
Fixed.
o as.solist
Crashed when x was a 'layered' object.
Fixed.
o linnet
Crashed in some trivial cases where there were no points or lines.
Fixed.
CHANGES IN spatstat VERSION 1.55-0
```

OVERVIEW

```
o We thank 'AdriMaz' and Nicholas Read for contributions.
o Lurking variable plot for models fitted to several point patterns.
o Improvements to code for class 'mppm'.
o Improvements to leverage and influence diagnostics.
o Improved summary information for funxy and distfun objects.
o Bug fixes and improvements.
o Removed old warnings and deprecated functions.
o Nickname: "Stunned Mullet"
```

NEW FUNCTIONS

```
o contour.leverage.ppm
Method for 'contour' for leverage functions of class 'leverage.ppm'
o lurking
New generic function for lurking variable plots.
o lurking.ppp, lurking.ppm
These are equivalent to the original function 'lurking'.
They are now methods for the new generic 'lurking'.
o lurking.mppm
New method for class 'mppm'
Lurking variable plot for models fitted to several point patterns.
o print.lurk
Prints information about the object returned by the function 'lurking'
representing a lurking variable plot.
o model.matrix.mppm
Method for 'model.matrix' for models of class 'mppm'.
o test.crossing.psp, test.selfcrossing.psp
Previously undocumented functions for testing whether segments cross.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o predict.ppm
Now recognises the arguments 'dimyx' and 'eps' for specifying the
resolution of the grid of prediction points.
o leverage.ppm, dfbetas.ppm
Increased the default resolution of the pixel images.
Spatial resolution can now be controlled by the arguments 'dimyx', 'eps'.
o ppmInfluence
The result now belongs to class 'ppmInfluence', for which there are
methods for 'leverage', 'influence', 'dfbetas' which extract the
desired component.
o plot.leverage.ppm
New argument 'what'.
o persp.leverage.ppm
New arguments 'zlab' and 'what'.
o as.im.leverage.ppm
New argument 'what'.
o summary.funxy, summary.distfun
Printed information now includes a summary of the function values.
o lurking.ppm
Accelerated.
o "[.psp"
Accelerated.
o clf.test, conspire, bounding.box, ksmooth.ppp, mpl, superimposePSP,
eval.hyper, smooth.fv, smooth.ppp, smooth.msr, rtoro, plot.kstest
These deprecated functions have now been removed.
o bermantest
This deprecated function has now been removed.
Use berman.test instead.
o kstest
This deprecated function has now been removed.
Use cdf.test instead.
o plot.ppp
A very old warning, about the interpretation of the mark scale
as the circle diameter, is no longer printed.
```

BUG FIXES

```
o nnmap, nnmark
Values were incorrect if the resulting pixel image
had unequal numbers of rows and columns.
Fixed.
o vcov.mppm
Format was incorrect (rows/columns were omitted) in some cases.
Fixed.
o model.matrix.ppm, model.frame.ppm
Values were sometimes incorrect when applied to the result of subfits().
To be precise, if 'fit' was an mppm object fitted to a hyperframe
that included 'design covariates' (covariates that take a constant value
in each row of the hyperframe), and if 'futs <- subfits(fit)', then
model.matrix(futs[[i]]) gave incorrect values in the columns
corresponding to the design covariates.
Fixed.
o model.matrix.ppm
The attribute 'assign' was omitted, in some cases.
Fixed.
o simulate.dppm, simulate.detpointprocfamily
In dimensions higher than 2, the result was shifted so that
it was centred at the origin.
Fixed.
o Smooth.ppp
Crashed if geometric=TRUE and there were several columns of marks.
Fixed.
o simulate.dppm, simulate.detpointprocfamily
Crashed if nsim > 1 and the spatial dimension was not equal to 2.
Fixed.
o plot.leverage.ppm
Contour line was annotated, which was not intended.
Fixed.
o leverage.ppm
The leverage function was oversmoothed, when the model was fitted
with method="logi".
Fixed.
CHANGES IN spatstat VERSION 1.54-0
```

OVERVIEW

```
o We thank Rochelle Constantine, Lily Kozmian-Ledward,
Ian Renner and Leigh Torres for contributions.
o New dataset 'cetaceans'.
o Gamma correction for colour maps and image plots.
o Class 'units' has been renamed 'unitname' to avoid package collision.
o Bug fix in leverage code
o Tighter bounding box for psp, lpp, linnet objects.
o Improved layout in plot.solist
o Tools to increase colour saturation.
o Connected components of a 3D point pattern.
o Accelerated computations on linear networks.
o Accelerated simulation of determinantal point processes.
o Improved printing of 3D point patterns.
o Minor corrections to handling of unitnames.
o Nickname: 'Vacuous Mission Statement'
```

NEW DATASETS

```
o cetaceans
Nine replicates of a marine survey in New Zealand,
consisting of recorded sightings of dolphins, whales and other species.
Generously contributed by Lily Kozmian-Ledward, Rochelle Constantine
and Leigh Torres.
```

NEW FUNCTIONS

```
o to.saturated
Convert a colour value to the corresponding fully-saturated colour.
o intensity.psp
Compute the average total length of segments per unit area.
o boundingbox.psp
Bounding box for line segment patterns.
This produces a tighter bounding box than the previous default behaviour.
o boundingbox.lpp
Bounding box for point patterns on a linear network.
This produces a tighter bounding box than the previous default behaviour.
o boundingbox.linnet
Bounding box for a linear network.
This produces a tighter bounding box than the previous default behaviour.
o "Frame<-.default"
New default method for assigning bounding frame to a spatial object.
o connected.pp3
Connected components of a 3D point pattern.
o colouroutputs, "colouroutputs<-"
Extract or assign colour values in a colour map.
(Documented a previously-existing function)
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o plot.im
New argument 'gamma' supports gamma correction of colour maps.
New argument 'ncolours' specifies the default number of colours.
o colourmap, lut
New argument 'gamma' supports gamma correction of colour maps.
o plot.solist, plot.anylist
New argument 'panel.vpad' controls vertical space for panel title
when equal.scales=FALSE.
o class 'units'
The class 'units' has been renamed 'unitname' to avoid a clash with
other packages.
o unitname
The generic function 'unitname' now returns an object of class 'unitname'.
o print.units, summary.units, print.summary.units, as.character.units,
compatible.units
These methods are now called print.unitname, summary.unitname,
print.summary.unitname, as.character.unitname and compatible.unitname.
o as.units
This function has been renamed 'as.unitname' and now returns
an object of class 'unitname'.
o rescale.units
This method has been renamed 'rescale.unitname' and now returns
an object of class 'unitname'.
o profilepl
New argument 'fast' controls the use of shorcuts.
o reload.or.compute
New argument 'force'.
o pixellate.ppp, pixellate.owin, pixellate.psp
New argument 'DivideByPixelArea'.
o density.psp
New argument 'at' determines locations where the density is evaluated.
o as.solist
as.solist(x) always returns an object of class 'solist',
removing any additional classes.
o lineardirichlet
Accelerated.
o integral.linim
Accelerated.
o "[.ppp", "[.lpp", "[.psp"
In the expression X[W] where W is a window,
if X has a unitname but W does not,
the result now inherits the unitname of X.
o distfun.ppp
New argument 'undef'.
o print.pp3
More informative output when x is marked.
```

BUG FIXES

```
o leverage.ppm, influence.ppm, dfbetas.ppm
Calculations were slightly incorrect for models fitted using the
border correction.
Fixed.
o integral.linim
Gave incorrect value in some extreme cases
(where many network segments were shorter than one pixel width).
Fixed.
o update.kppm
Did not function correctly when several additional arguments were given.
Fixed.
o plot.solist
Panel titles were cut off, when equal.scales=FALSE (the default).
Fixed.
o intersection.owin, union.owin, setminus.owin
The result sometimes did not inherit the correct 'unitname'.
Fixed.
CHANGES IN spatstat VERSION 1.53-2
```

OVERVIEW

```
o We thank Christophe Biscio and Rasmus Waagepetersen for contributions.
o Correction to 'lohboot'
o Improvements to ppm and update.ppm
o Bug fixes and minor improvements.
o Nickname: "Quantum Entanglement"
```

NEW FUNCTIONS

```
o fitin.profilepl
Extract the fitted interaction from a model fitted by profile likelihood.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o lohboot
Algorithm has been corrected and extended
thanks to Christophe Biscio and Rasmus Waagepetersen.
New arguments 'block', 'basicboot', 'Vcorrection'.
o ppm.ppp, ppm.quad
New argument 'clipwin'
o update.ppm
For the case 'update(model, X)' where X is a point pattern,
if the window of X is different from the original window,
then the model is re-fitted from scratch (i.e. use.internal=FALSE).
o plot.leverage.ppm
A contour line showing the average value of leverage
is now drawn on the colour ribbon, as well as on the main image.
New argument 'args.contour'.
```

BUG FIXES

```
o lohboot
Implementation was completely incorrect.
[Spotted and fixed by Christophe Biscio and Rasmus Waagepetersen.]
Fixed.
o update.ppm
Did not always work correctly with formulae that included 'polynom()' terms.
Fixed.
CHANGES IN spatstat VERSION 1.53-1
```

OVERVIEW

```
o We thank Suman Rakshit for contributions.
o Bug fix in plot.linim
o Nickname: "Drongo"
```

BUG FIXES

```
o plot.linim
Colour map was mangled if log=TRUE.
Fixed.
CHANGES IN spatstat VERSION 1.53-0
```

OVERVIEW

```
o We thank Tilman Davies and Mehdi Moradi for contributions.
o Numerous bug fixes for linear networks code.
o spatstat now requires the sub-package 'spatstat.data'
which contains the datasets.
o Minor enhancements and bug fixes.
o Nickname: "Tinfoil Hat"
```

NEW FUNCTIONS

```
o "[<-.linim"
Subset assignment method for pixel images on a linear network.
o nnfromvertex
Given a point pattern on a linear network,
find the nearest data point from each vertex of the network.
o tile.lengths
Calculate the length of each tile in a tessellation on a network.
o text.ppp, text.lpp, text.psp
Methods for 'text' for spatial patterns.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o datasets
All datasets installed in 'spatstat' have now been moved
into the sub-package 'spatstat.data'. This should not have any effect
on normal use. The 'spatstat.data' package is automatically loaded
when spatstat is loaded, and the datasets are lazy-loaded so that
they are available in the usual way. To list all datasets you now need
to type 'data(package="spatstat.data")'
o nbfires
This dataset now includes information about the different
land and sea borders of New Brunswick.
o rhohat
New argument 'subset' allows computation for a subset of the data.
o predict.lppm
Argument 'locations' can now be an 'lpp' object.
o ewcdf
Argument 'weights' can now be NULL.
o plot.msr
New arguments 'equal.markscale' and 'equal.ribbon'.
o plot.im
The number of tick marks in the colour ribbon can now be controlled
using the argument 'nint' in 'ribargs'.
o plot.symbolmap
New argument 'nsymbols' controls the number of symbols plotted.
o square
Handles a common error in the format of the arguments.
o [.linim
More robust against artefacts.
o [.linnet
More robust against artefacts when the subset index is a pixel mask.
o linim
The image Z is now automatically restricted to the network.
New argument 'restrict'.
o plot.linim
When style="width", negative values are plotted in red (by default).
New argument 'negative.args' controls this.
o plot.linim
New argument 'zlim' specifies the range of values to be mapped.
o Summary.linim
Recognises the argument 'finite' so that range(x, finite=TRUE)
works for a linim object x.
o identify.psp
Improved placement of labels.
Arguments can be passed to text.default to control the plotting of labels.
o as.polygonal
Accelerated when w is a pixel mask.
o density.lpp
Accelerated in the default case.
o Kinhom
Stops gracefully if 'lambda' contains any zero values.
o print.linim
Prints more information.
```

BUG FIXES

```
o with.msr
The value of 'atommass' was incorrect, due to a coding error.
Fixed.
o [.linim
Internal data was sometimes corrupted.
Fixed.
o as.linim
The result had incorrect internal format when Window(X) was a mask
and one of the arguments 'eps', 'dimyx', 'xy' was present.
Fixed.
o as.im.im
If W was a rectangle or polygonal window, the pixel resolution of the
result was determined by the spatstat defaults, rather than being
determined by the image argument X. This was contrary to the
rule advertised in help(as.im).
Fixed.
o density.lpp
In the 'slow' case (kernel not Gaussian, or continuous=FALSE),
occasionally a pixel could incorrectly be assigned the value 1.
[Spotted by Mehdi Moradi.]
Fixed.
o "[.solist"
Ignored the "..." arguments in some cases.
Fixed.
o density.lpp
Ignored the resolution arguments 'eps', 'dimyx' in the default case.
Fixed.
o plot.msr
Plotted the panel titles on top of each other, if how="contour".
Fixed.
o contour.im
Plotted the title text at the wrong place when add=TRUE and show.all=TRUE.
Fixed.
o predict.lppm
Crashed if 'locations' was an 'lpp' object.
Fixed.
o plot.ppp
Crashed if the window had height 0 and width 0
and the pattern had several columns of marks.
Fixed.
o plot.solist
Crashed if all panels had windows of height 0 and width 0.
Fixed.
o linearK, linearKinhom, linearpcf, linearpcfinhom
Crashed if the linear network was disconnected and one component
of the network contained fewer than 2 points.
Fixed.
o integral.linim
Crashed in some cases.
Fixed.
o "[.linim"
Crashed in some cases.
Fixed.
CHANGES IN spatstat VERSION 1.52-1
```

OVERVIEW

```
o Bug fix to satisfy the development version of R.
o Nickname: "Apophenia"
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o Ops.imlist
Improved the 'names' of the result.
```

BUG FIXES

```
o bw.smoothppp
Crashes in R-devel.
Fixed.
CHANGES IN spatstat VERSION 1.52-0
```

OVERVIEW

```
o We thank Nicholas Read, Abdollah Jalilian, Suman Rakshit,
Dominic Schuhmacher and Rasmus Waagepetersen for contributions.
o Important bug fixes.
o Now handles disconnected linear networks.
o Effect function is now available for all types of fitted model.
o A model can be fitted or re-fitted to a sub-region of data.
o More support for measures.
o 'Pool' operations improved.
o Geometric-mean smoothing.
o Changed algorithm defaults in ippm.
o Version nickname: "Rudimentary Lathe"
```

NEW FUNCTIONS

```
o as.data.frame.envelope
Extract function data from an envelope object,
including the functions for the simulated data ('simfuns')
if they were saved.
o is.connected, is.connected.default, is.connected.linnet
Determines whether a spatial object consists of
one topologically connected piece, or several pieces.
o is.connected.ppp
Determines whether a point pattern is connected after
all pairs of points closer than distance R are joined.
o hist.funxy
Histogram of values of a spatial function.
o model.matrix.ippm
Method for 'model.matrix' which allows computation of
regular and irregular score components.
o harmonise.msr
Convert several measures (objects of class 'msr')
to a common quadrature scheme.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o Smooth.ppp
New argument 'geometric' supports geometric-mean smoothing.
o Kinhom
New argument 'ratio'.
o linearKinhom, linearpcfinhom
Changed default behaviour when 'lambda' is a fitted model.
New arguments 'update' and 'leaveoneout'.
o linearK, linearKinhom, linearpcf, linearpcfinhom, compilepcf
Ratio calculations are now supported.
New argument 'ratio'.
o effectfun
Now works for 'ppm', 'kppm', 'lppm', 'dppm', 'rppm' and 'profilepl' objects.
o ppm, kppm
The argument 'subset' can now be a window (class 'owin')
specifying the subset of data to which the model should be fitted.
o fitted.lppm
New argument 'leaveoneout' allows leave-one-out computation of fitted value.
o pool.rat
New arguments 'relabel' and 'variance'.
o density.lpp
The return value is a pixel image of class 'linim' in all cases.
o plot.linim, plot.linfun
A scale bar is now plotted when style="width".
New argument 'legend'.
o ippm
Default values for the parameters of the optimisation algorithm (nlm.args)
have changed.
o ippm
The internal format of the result has been extended slightly.
o bind.fv
New argument 'clip'.
o as.im.distfun
New argument 'approx' specifies the choice of algorithm.
o "[.psp"
New argument 'fragments' specifies whether to keep fragments of
line segments that are cut by the new window, or only to retain
segments that lie entirely inside the window.
o predict.rhohat
New argument 'what' determines which value should be calculated:
the function estimate, the upper/lower confidence limits, or the
standard error.
o pool.fv
New arguments 'relabel' and 'variance'
o pool.rat
New argument 'weights'.
o plot.msr
New argument 'massthresh'.
o Ops.msr
Calculations like A+B can now be performed even when the measures A and B
are not defined on the same quadrature scheme.
o density.ppp
New argument 'verbose'.
o bw.pcf
New argument 'verbose'.
o hist.im
New argument 'xname'.
o [.leverage.ppm
New argument 'update'.
o [.layered
Additional arguments '...' are now passed to other methods.
o logLik.ppm
The warning about pseudolikelihood ('log likelihood not available')
is given only once, and is not repeated in subsequent calls,
within a spatstat session.
o kppm
Refuses to fit a log-Gaussian Cox model with anisotropic covariance.
o plot.linim, plot.linfun
The return value has a different format.
Arguments have been renamed and reorganised.
o density.lpp
New argument 'old'.
o ippm
Accelerated.
o Smooth.ppp
Now exits gracefully if any mark values are NA, NaN or Inf.
o timeTaken
Now exits gracefully if there is no timing information.
o nbfires
The unit of length for the coordinates is now specified in this dataset.
```

BUG FIXES

```
o bw.pcf
Results were totally incorrect due to a typo.
[Spotted by Abdollah Jalilian and Rasmus Waagepetersen.]
Fixed.
o predict.rho2hat
Results were incorrect for a rho2hat object computed from a point pattern.
Fixed.
o density.ppp
If the smoothing bandwidth was very small (e.g.\ smaller than pixel width),
results were inaccurate if the default resolution was used,
and completely wrong if another resolution was specified.
[Spotted by Dominic Schuhmacher.]
Fixed.
o linearK, linearKinhom, linearpcf, linearpcfinhom, linearKcross,
linearKdot, linearpcfcross, linearpcfdot, linearKcross.inhom,
linearKdot.inhom, linearpcfcross.inhom, linearpcfdot.inhom
Crashed if the network was disconnected.
Fixed.
o crossdist.lpp
Crashed if the network was disconnected.
Fixed.
o countends
Crashed if the network was disconnected.
Fixed.
o model.images.ppm
Crashed for models fitted using 'covfunargs'.
Fixed.
o model.matrix.ppm
Crashed for models fitted using 'covfunargs',
if argument 'Q' was given.
Fixed.
o polynom
Expansion of some polynomials caused an error message
about 'invalid model formula'.
Fixed.
o plot.ppp
The argument 'type="n"' did not suppress plotting of the legend,
for marked point patterns.
Fixed.
o plot.psp
Ignored 'show.all' when 'add=TRUE'.
Fixed.
o intensity.ppm
Result had incorrect 'names' attribute in some cases.
Fixed.
o marks<-.ppx
The assignment marks(X) <- a, where 'a' is a single atomic value,
caused an error if 'X' contained zero points.
Fixed
o model.depends
Crashed when applied to regression models fitted by 'gam',
or point process models fitted by 'ppm' with 'use.gam=TRUE'.
Fixed.
o pool.fv
Crashed sometimes, if the arguments did not have the same set of
column names.
Fixed.
o pool.rat
Crashed with an error message from 'fmt'
if there were more than 20 objects to be pooled.
Fixed.
o linearK
The 'theo' column was missing if npoints(X) < 2 and correction="Ang".
Fixed.
o model.matrix.ppm
Result was malformed if the model was fitted with 'use.gam=TRUE'.
Fixed.
o effectfun
Crashed if 'covname' was omitted,
if the model was fitted with 'use.gam=TRUE'.
Fixed.
o nncross.lpp
Result had incorrect format if Y was empty, in some cases.
Fixed.
o linearKinhom
Plot label for y axis was incorrect.
[Spotted by Suman Rakshit.]
Fixed.
o plot.solist
If the entries were 'linim' objects, they were plotted using image()
so arguments like 'style="w"' were ignored.
Fixed.
o as.ppp.data.frame
Crashed if X was an object of class 'tbl_df' from the dplyr package.
Fixed.
o plot.lpp
Crashed if there were multiple columns of marks.
Fixed.
CHANGES IN spatstat VERSION 1.51-0
```

OVERVIEW

```
o We thank Greg McSwiggan, Mehdi Moradi and Tammy L Silva for contributions.
o New fast algorithm for kernel smoothing on a linear network.
o Leverage and influence diagnostics extended to Poisson/Gibbs models
fitted by logistic composite likelihood.
o Two-stage Monte Carlo test.
o Dirichlet/Voronoi tessellation on a linear network.
o Thinning of point patterns on a linear network.
o More support for functions and tessellations on a linear network.
o Improvements and bug fixes.
o Version nickname: 'Poetic Licence'
```

NEW FUNCTIONS

```
o bits.test:
Balanced Independent Two-Stage Monte Carlo test,
an improvement on the Dao-Genton test.
o lineardirichlet
Computes the Dirichlet-Voronoi tessellation associated with a
point pattern on a linear network.
o domain.lintess, domain.linfun
Extract the linear network from a 'lintess' or 'linfun' object.
o summary.lintess
Summary of a tessellation on a linear network.
o clicklpp
Interactively add points on a linear network.
o envelopeArray
Generate an array of envelopes using a function that returns 'fasp' objects.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o density.lpp
New fast algorithm (up to 1000 times faster) for the default case
where kernel="gaussian" and continuous=TRUE.
Generously contributed by Greg McSwiggan.
o leverage.ppm, influence.ppm, dfbetas.ppm
These methods now work for models that were fitted by logistic
composite likelihood (method='logi').
o rthin
Argument X can now be a point pattern on a linear network (class 'lpp').
o fitted.ppm
New option: type = "link"
o update.kppm
New argument 'evaluate'.
o integral.linfun
New argument 'delta' controls step length of approximation to integral.
o as.linim.default
New argument 'delta' controls spacing of sample points in internal data.
o as.linfun.lintess
New argument 'values' specifies the function value for each tile.
New argument 'navalue'.
```

BUG FIXES

```
o leverage.ppm, influence.ppm, dfbetas.ppm
Results for Gibbs models were incorrect due to a mathematical error.
(Results for Poisson models were correct).
Fixed.
o leverage.ppm, influence.ppm, dfbetas.ppm, ppmInfluence
Calculations were incorrect for a Geyer model fitted using
an edge correction other than "border" or "none".
Fixed.
o step, kppm, update.kppm
'step' did not work for kppm objects in some cases
due to a scoping problem in update.kppm.
Fixed.
o improve.kppm
Crashed if the window was not a rectangle.
Fixed.
o pcf.ppp, pcfinhom
Crashed if kernel="epa" rather than "epanechnikov".
Fixed.
o alltypes
Crashed if envelope=TRUE and reuse=FALSE.
Fixed.
o pairdist.lpp, nndist.lpp, nnwhich.lpp, nncross.lpp
Crashed if the network was disconnected.
Fixed.
o as.im.linim, as.linim.linim
Additional arguments such as 'eps' and 'dimyx' were ignored.
Fixed.
o as.im.default
Arguments 'eps and 'xy' were ignored if X was a single numeric value.
Fixed.
o 'timed' class
Printing of these objects did not work in some locales.
Fixed.
o runifpoint
Ignored 'drop' argument if the window was a rectangle.
Fixed.
CHANGES IN spatstat VERSION 1.50-0
```

OVERVIEW

```
o We thank Richard Cotton, Adrian Heyner, Abdollah Jalilian,
Dominic Schuhmacher and Rasmus Waagepetersen for contributions.
o spatstat now 'Imports' the package 'spatstat.utils'.
o Bandwidth selection for pair correlation function.
o Improvements and bug fixes.
o Version nickname: 'Bunyip Aristocracy'
```

NEW PACKAGE STRUCTURE

```
o spatstat is being split into several sub-packages, to satisfy
the requirements of CRAN. This should not affect the user:
existing code will continue to work in the same way.
Currently there are two sub-packages, called 'spatstat.utils'
and 'spatstat'. Typing 'library(spatstat)' will load the familiar
'spatstat' package which can be used as before, and will silently
import the 'spatstat.utils' package. The 'spatstat.utils' package
contains utility functions that were originally written for 'spatstat':
they were undocumented internal functions in 'spatstat', but are now
documented and accessible in a separate package because they may be
useful for other purposes. To access these functions, you need to
type 'library(spatstat.utils)'.
```

NEW FUNCTIONS

```
o bw.pcf
Bandwidth selection for pair correlation function.
Original code contributed by Abdollah Jalilian and Rasmus Waagepetersen.
o grow.box3
Expand a three-dimensional box.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o as.owin
Now refuses to convert a 'box3' to a two-dimensional window.
o pixellate.ppp
If the pattern is empty, the result is an integer-valued image
(by default) for consistency with the results for non-empty patterns.
o ppp
If the coordinate vectors x and y contain NA, NaN or infinite values,
these points are deleted with a warning, instead of causing a fatal error.
o ppm
Argument 'interaction' can now be a function that makes an interaction,
such as Poisson, Hardcore, MultiHard.
o pcf, pcfinhom
New argument 'close' for advanced use.
o runifpointx, rpoisppx
New argument 'drop'.
o shapley, ponderosa
In these installed datasets, the functions shapley.extra$plotit
and ponderosa.extra$plotit have changed slightly (to accommodate the
dependence on the package spatstat.utils).
o kppm
Improved printed output.
```

BUG FIXES

```
o rMaternI, rMaternII
If 'win' was a three-dimensional box of class 'box3',
the result was a two-dimensional point pattern.
[Spotted by Adrian Heyner.]
Fixed.
o rmhmodel.ppm, simulate.ppm
Crashed when applied to a fitted Lennard-Jones model.
[Spotted by Dominic Schuhmacher.]
Fixed.
o leverage.ppm, influence.ppm, dfbetas.ppm
Crashed when applied to some hard-core models.
Fixed.
o "[.ppx"
The format of the result was slightly malformed
if exactly one point was selected.
Fixed.
o unmark.lpp, marks<-.lpp
The result had class c("lpp", "lpp", "ppx") instead of c("lpp", "ppx").
Fixed.
CHANGES IN spatstat VERSION 1.49-0
```

OVERVIEW

```
o We thank Tilman Davies, Kassel Hingee, Abdollah Jalilian,
Brian Ripley and Dominic Schuhmacher for contributions.
o spatstat now 'Suggests' the package 'fftwtools'.
o Operations on signed measures.
o Operations on lists of pixel images.
o Improved pixellation of point patterns.
o Stieltjes integral extended.
o Subset operators extended.
o Greatly accelerated 'rmh' when using 'nsave'
o Some computations accelerated.
o Size of namespace reduced, for efficiency.
o Bug fixes.
o Version nickname: 'So-Called Software'
```

NEW DEPENDENCIES

```
o fftwtools
spatstat now 'Suggests' the package 'fftwtools'.
This package provides a very fast implementation of
the Fast Fourier Transform, leading to much faster computation
in the spatstat functions 'density.ppp', 'relrisk.ppp', 'convolve.im',
'blur', 'scan.test' and many other functions.
The 'fftwtools' package requires the external software library 'fftw'.
We strongly recommend installing this library if possible.
```

NEW FUNCTIONS

```
o hexagon, regularpolygon
Create regular polygons.
o Ops.msr
Arithmetic operations for measures.
o Math.imlist, Ops.imlist, Summary.imlist, Complex.imlist
Arithmetic operations for lists of pixel images.
o measurePositive, measureNegative, measureVariation, totalVariation
Positive and negative parts of a measure, and variation of a measure.
o as.function.owin
Convert a spatial window to a function (x,y), the indicator function.
o as.function.ssf
Convert an object of class 'ssf' to a function(x,y)
o as.function.leverage.ppm
Convert an object of class 'leverage.ppm' to a function(x,y)
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o stieltjes
Argument 'M' can be a stepfun object (such as an empirical CDF).
o quantile.ewcdf
The function is now normalised to the range [0,1]
before the quantiles are computed.
This can be suppressed by setting normalise=FALSE.
o pixellate.ppp
New arguments 'fractional' and 'preserve' for more accurate discretisation.
o "[.layered"
Subset index i can now be an 'owin' object.
o "[.solist"
Subset index i can now be an 'owin' object.
o plot.solist, plot.imlist, plot.anylist
Result is now an (invisible) list containing the result
from executing the plot of each panel.
o ppp
New argument 'checkdup'.
o Summary.im
Argument 'na.rm' is no longer ignored.
o cdf.test
The methods for classes ppp, ppm, lpp, lppm, slrm
have a new argument 'interpolate'.
o as.solist
The argument x can now be a spatial object;
as.solist(cells) is the same as solist(cells).
o bw.diggle, bw.ppl, bw.relrisk, bw.smoothppp
These functions now extract and store the name of the unit of length
from the point pattern dataset. When the bandwidth selection criterion
is plotted, the name of the unit of length is shown on the x-axis.
o polynom
This function now has a help file.
o rmhcontrol
New parameter 'pstage' determines when to generate random proposal points.
o rmh
Accelerated, in the case where multiple patterns are saved using 'nsave'.
o bdist.pixels
Accelerated for polygonal windows. New argument 'method'.
o spatstat namespace
The namespace of the spatstat package has been shortened
(by internally registering the native routines) which should
make the package run faster.
o sum.im, range.im, max.im, min.im
These functions have been removed, as they are now subsumed in Summary.im.
```

BUG FIXES

```
o plot.msr
If one of 'nrows' or 'ncols' was specified, but not both,
an obscure error occurred.
Fixed.
o plot.solist, plot.imlist, plot.anylist
Crashed if 'nrows' and 'ncols' were given values implying
that some rows or columns would not contain any plots.
Fixed.
o as.ppp.lpp
Crashed if there was more than one column of marks.
Fixed.
o has.close.pp3
Results were incorrect, or a crash occurred, when argument 'Y' was given.
Fixed.
o rmpoispp
If 'lambda' was a list of images, 'names(lambda)' was ignored,
rather than serving as the default value of 'types'.
Fixed.
o bugfixes
Output was garbled, in rare cases.
Fixed.
o kppm
Result was malformed when clusters="VarGamma" and method="clik2".
Spotted by Abdollah Jalilian.
Fixed.
o QQversion
Plotting labels were malformed.
Fixed.
CHANGES IN spatstat VERSION 1.48-0
```

OVERVIEW

```
o We thank Kim Colyvas, Yongtao Guan, Gopalan Nair,
Nader Najari, Suman Rakshit, Ian Renner and Hangsheng Wang
for contributions.
o Sufficient Dimension Reduction for point processes.
o Alternating Gibbs Sampler for point process simulation.
o Intensity approximation for area-interaction and Geyer models.
o New class of spatially sampled functions.
o ROC and AUC extended to other types of point patterns and models.
o More support for linear networks.
o More support for infinite straight lines.
o Simulation of 'rhohat' objects.
o Kernel smoothing accelerated.
o Methods for 'head' and 'tail' for spatial patterns.
o More low-level functionality.
o Improvements and bug fixes.
o spatstat now has more than 1000 help files.
o Nickname: 'Model Prisoner'
```

NEW CLASSES

```
o ssf
Class of spatially sampled functions.
```

NEW FUNCTIONS

```
o sdr, dimhat
Sufficient Dimension Reduction for point processes.
Matlab code contributed by Yongtao Guan, translated by Suman Rakshit.
o rags, ragsAreaInter, ragsMultiHard
Alternating Gibbs Sampler for point processes.
o psib
Sibling probability (index of clustering strength in a cluster process).
o bugfixes
List all bug fixes in recent versions of a package.
o roc.kppm, roc.lppm, roc.lpp
Methods for 'roc' (receiver operating characteristic curve)
for fitted models of class 'kppm' and 'lppm'
and point patterns of class 'lpp'
o auc.kppm, auc.lppm, auc.lpp
Methods for 'auc' (area under the ROC curve)
for fitted models of class 'kppm' and 'lppm'
and point patterns of class 'lpp'
o rlpp
Random points on a linear network with a specified probability density.
o cut.lpp
Method for 'cut' for point patterns on a linear network.
o crossing.linnet
Find crossing points between a linear network and another set of lines.
o ssf
Create a spatially sampled function
o print.ssf, plot.ssf, contour.ssf, image.ssf
Display a spatially sampled function
o as.im.ssf, as.ppp.ssf, marks.ssf, marks<-.ssf, unmark.ssf, [.ssf, with.ssf
Manipulate data in a spatially sampled function
o Smooth.ssf
Smooth a spatially sampled function
o integral.ssf
Approximate integral of spatially sampled function
o simulate.rhohat
Generate a Poisson random point pattern with intensity that is
a function of a covariate, given by a 'rhohat' object.
o head.ppp, head.ppx, head.psp, head.tess,
tail.ppp, tail.ppx, tail.psp, tail.tess
Methods for 'head' and 'tail' for spatial patterns.
o as.data.frame.tess
Convert a tessellation to a data frame.
o timeTaken
Extract the timing data from a 'timed' object or objects.
o rotate.infline, shift.infline, reflect.infline, flipxy.infline
Geometrical transformations for infinite straight lines.
o whichhalfplane
Determine which side of an infinite line a point lies on.
o points.lpp
Method for 'points' for point patterns on a linear network.
o pairs.linim
Pairs plot for images on a linear network.
o has.close
Faster way to check whether a point has a close neighbour.
o closetriples
Low-level function to find all close triples of points.
o matrixpower, matrixsqrt, matrixinvsqrt
Raise a matrix to any power.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o intensity.ppm
Intensity approximation is now available for the Geyer saturation process
and the area-interaction process (results of research with Gopalan Nair).
o envelope.lpp, envelope.lppm
New arguments 'fix.n' and 'fix.marks' allow envelopes to be computed
using simulations conditional on the observed number of points.
o "[.im"
The subset index "i" can now be a linear network (object of class 'linnet').
The result of "x[i, drop=FALSE]" is then a pixel image of class 'linim'.
o cut.ppp
Argument z can be "x" or "y" indicating one of the spatial coordinates.
o rThomas, rMatClust, rCauchy, rVarGamma, rPoissonCluster, rNeymanScott
New argument 'saveparents'.
o lintess
Argument 'df' can be missing or NULL,
resulting in a tesellation with only one tile.
o lpp
X can be missing or NULL, resulting in an empty point pattern.
o plot.lintess
Improved plot method, with more options.
o rpoisline
Also returns information about the original infinite random lines.
o density.ppp, Smooth.ppp
Accelerated.
o density.psp
New argument 'method' controls the method of computation.
New faster option 'method="FFT"'
o nndist.lpp
Accelerated.
```

BUG FIXES

```
o F3est
Estimates of F(r) for the largest value of r were wildly incorrect.
Fixed.
o clip.infline
Results were incorrect unless the midpoint of the window
was the coordinate origin.
Fixed.
o integral.linim
Results were inaccurate if many of the segment lengths were
shorter than the width of a pixel.
Fixed.
o predict.lppm
Bizarre error messages about 'class too long' or 'names too long'
occurred if the model was multitype.
Fixed.
o superimpose
Point patterns containing 0 points were ignored
when determining the list of possible marks.
Fixed.
o chop.tess
Vertical lines were not handled correctly
with pixellated tessellations.
Fixed.
o timed
Argument 'timetaken' was ignored.
Fixed.
o ppm
Crashed if method="logi" and the 'covariates' were a data frame.
[Spotted by Kim Colyvas and Ian Renner.]
Fixed.
o rpoislpp, runiflpp
Crashed if nsim > 1.
Fixed.
o rpoisline
Crashed if zero lines were generated.
Fixed.
o model.frame.ppm
Crashed if the original model was fitted to a data frame of covariates
and there were NA's amongst the covariate values.
[Spotted by Kim Colyvas.]
Fixed.
o any, all
When applied to pixel images (objects of class 'im') the result
was sometimes NA when a finite value should have been returned.
Fixed.
o predict.rhohat
When the original data were on a linear network,
the result of predict.rhohat did not belong to the correct class 'linim'.
Fixed.
CHANGES IN spatstat VERSION 1.47-0
```

OVERVIEW

```
o We thank Marcel Austenfeld, Guy Bayegnak, Tilman Davies, Cenk Icos,
Jorge Mateu, Frederico Mestre, Mehdi Moradi, Virginia Morera Pujol,
Suman Rakshit and Sven Wagner for contributions.
o Non-Gaussian smoothing kernels.
o Important bug fix in linearK, linearpcf
o Changed internal format of linnet and lpp objects.
o Faster computation in linear networks.
o Bias correction techniques.
o Bounding circle of a spatial object.
o Minkowski sum also applicable to point patterns and line segment patterns.
o Option to plot marked points as arrows.
o Kernel smoothing accelerated.
o Workaround for bug in some graphics drivers affecting image orientation.
o Bug fixes and improvements.
o Version nickname: 'Responsible Gambler'
```

NEW FUNCTIONS

```
o anyNA.im
Method for 'anyNA' for pixel images.
o bc
Bias correction (Newton-Raphson) for fitted model parameters.
See also 'rex'.
o boundingcircle, boundingcentre
Find the smallest circle enclosing a window or point pattern.
o "[.linim"
Subset operator for pixel images on a linear network.
o mean.linim, median.linim, quantile.linim
The mean, median, or quantiles of pixel values in a
pixel image on a linear network.
o rex
Richardson extrapolation for numerical integrals and
statistical model parameter estimates.
o weighted.median, weighted.quantile
Median or quantile of numerical data with associated weights.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o linear networks
The internal format of a 'linnet' (linear network) object
has been changed. Existing datasets of class 'linnet' and 'lpp'
are still supported. However, computation will be faster if they
are converted to the new format. To convert a linnet object L
to the new format, use L <- as.linnet(L). To convert an lpp object X
to the new format, use X <- as.lpp(X).
o density.ppp, Smooth.ppp
New argument 'kernel' allows the user to specify the smoothing kernel.
o density.ppp, Smooth.ppp
Argument 'weights' can now be a pixel image.
o MinkowskiSum, %(+)%
Now accepts arguments which are point patterns or line segment patterns
as well as windows.
o plot.im
New argument 'workaround' to avoid a bug in some device drivers
that causes the image to be displayed in the wrong spatial orientation.
[Thanks to Marcel Austenfeld for drawing attention to this.]
o sumouter
New argument 'y' allows computation of asymmetric outer products.
o linearKinhom, linearpcfinhom
New argument 'normpower'.
o rmh.default, rmh.ppm
New arguments 'nsim', 'saveinfo'.
o symbolmap, plot.ppp, plot.lpp
New option: shape="arrows"
o rcellnumber
New argument 'mu'.
o lengths.psp
New argument 'squared'.
o plot.linfun
Now passes arguments to the function being plotted.
o as.linnet.psp
If the line segment pattern has marks, then the resulting linear network
also carries these marks in the $lines component.
o summary.owin, summary.im
The fraction of frame area that is occupied by the window/image
is now reported.
o density.ppp, Smooth.ppp
Computation accelerated by about 15%
in the case where at='points' and kernel='gaussian'.
o linearK, linearpcf
Accelerated by about 40%.
o pixellate.ppp
Accelerated in the case where weights are given
o density.ppp
Accelerated in the cases where weights are given or 'diggle=TRUE'
o dilation.ppp
Improved geometrical accuracy.
Now accepts arguments to control resolution of polygonal approximation.
o discs
New argument 'npoly'.
Accelerated in some cases.
o plot.pp3
New arguments 'box.front', 'box.back' control plotting of the box.
o grow.rectangle
New argument 'fraction'.
o nnfun.lpp
New argument 'k'.
o bw.ppl
New argument 'sigma'.
o lppm
New argument 'random' controls placement of dummy points.
o rhohat.lpp
New argument 'random' controls placement of dummy points.
o quadrat.test.ppm
Accelerated in the case where the original window is a rectangle.
o kppm, mincontrast, cauchy.estpcf, lgcp.estpcf, matclust.estpcf,
thomas.estpcf, vargamma.estpcf
A warning about infinite values of the summary function
no longer occurs when the default settings are used.
o circumradius
This function is now deprecated, in favour of 'boundingradius'
o print.quad
More information is printed.
```

BUG FIXES

```
o linearK, linearpcf, and relatives:
These functions were sometimes greatly underestimated
when the network had segments shorter than 10 coordinate units.
[Bug introduced in spatstat 1.44-0, december 2015.]
Fixed.
o integral.linim, integral.linfun
Results were slightly inaccurate because of a bias in the
distribution of sample points.
[Bug introduced in spatstat 1.41-0, february 2015.]
Fixed.
o intensity.ppm
Result was incorrect for Gibbs models if the model was *exactly*
equivalent to a Poisson process (i.e. if all interaction
coefficients were exactly zero).
[Bug introduced in spatstat 1.28-1, june 2012.]
Fixed.
o rSSI
Sometimes terminated prematurely.
[Spotted by Frederico Mestre.]
Fixed.
o perspPoints
Crashed if the image Z contained NA
(i.e. if Z was only defined on a subset of the bounding frame).
Spotted by Guy Bayegnak.
Fixed.
o plot.ppp, plot.lpp
Crashed if the argument 'shape' was given.
Fixed.
o plot.kppm
Crashed if the model was not fitted by minimum contrast.
Fixed.
o superimpose
Crashed if the argument was a 'solist' containing line segment patterns.
Fixed.
o Jest
Crashed sometimes, depending on the shape of the observation window.
[Spotted by Cenk Icos.]
Fixed.
o plot.studpermutest
Crashed when the summary statistic was a multitype pair correlation
function or multitype K function. [Spotted by Sven Wagner.]
Fixed.
o pool.anylist
Crashed with a message about buffer size,
if the list was longer than about 100 items.
Fixed.
o diagnose.ppm, plot.diagppm
Crashed in some cases when cumulative=FALSE.
Fixed.
o leverage.ppm, influence.ppm, dfbetas.ppm
Crashed sometimes with a message about wrong replacement length.
[Spotted by Virginia Morera Pujol.]
Fixed.
o as.linnet.psp
Crashed with marked segment patterns, if any segments were very short.
[Spotted by Suman Rakshit.]
Fixed.
o stieltjes
Returned NA if some values of f were not finite.
Fixed.
o plot.symbolmap
If a new plot window was initialised, it was sometimes too small
to contain the geometric figures (circles, squares etc) in the symbol map.
Fixed.
o plot.ppp, plot.im
Ignored xlim, ylim.
Fixed.
o rhohat.lpp
Ignored nd, eps.
Fixed.
o nnfun.lpp
Print method gave incorrect information about the point pattern.
Fixed.
o "[.fv"
The default plot formula was not updated.
Fixed.
o fitted.ppm
The result was sometimes a 1-dimensional array rather than a numeric vector.
Fixed.
CHANGES IN spatstat VERSION 1.46-1
```

OVERVIEW

```
o Important bug fix.
o Version nickname: 'Spoiler Alert'
```

BUG FIXES

```
o density.ppp, Smooth.ppp
The results of density(X, at="points") and Smooth(X, at="points")
were incorrect in some cases. The contribution from the
left-most data point (the point with the smallest x coordinate)
was omitted. [Bug introduced in spatstat 1.26-0, April 2012.]
Fixed.
CHANGES IN spatstat VERSION 1.46-0
```

OVERVIEW

```
o We thank Corey Anderson and Sebastian Meyer for contributions.
o spatstat now depends on R 3.3.0 or later.
o Improvements to inhomogeneous multitype K and L functions.
o Variance approximation for pair correlation function.
o Leverage and influence for multitype point process models.
o Functions for extracting components of vector-valued objects.
o Important bug fix in Smooth.ppp
o Minor improvements and bug fixes.
o Version nickname: 'Multidimensional Toothbrush'
```

NEW FUNCTIONS

```
o split.msr
Decompose a measure into parts.
o unstack.msr
Decompose a vector-valued measure into its component measures.
o unstack.ppp, unstack.psp, unstack.lpp
Given a spatial pattern with several columns of marks,
separate the columns and return a list of spatial patterns,
each having only one column of marks.
o kernel.squint
Integral of squared kernel, for the kernels used in density estimation.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o Kcross.inhom, Kdot.inhom, Kmulti.inhom, Ldot.inhom, Lcross.inhom
These functions now allow intensity values to be given by
a fitted point process model.
New arguments 'update', 'leaveoneout', 'lambdaX'.
o diagnose.ppm
Infinite values of 'rbord' are now ignored and treated as zero.
This ensures that diagnose.ppm has a sensible default
when the fitted model has infinite reach.
o pcf.ppp
Now calculates an analytic approximation to the variance of
the estimate of the pair correlation function (when var.approx=TRUE).
Now returns the smoothing bandwidth used, as an attribute of the result.
o plot.ppp
When 'clipwin' is given, any parts of the boundary of the window of x
that lie inside 'clipwin' will also be plotted.
o plot.msr
Now handles multitype measures.
New argument 'multiplot'.
o plot.anylist
If a list entry x[[i]] belongs to class 'anylist', it will be expanded
so that each entry x[[i]][[j]] will be plotted as a separate panel.
o influence.ppm, leverage.ppm
These can now be applied to multitype point process models
and the results can be plotted.
o plot.influence.ppm, plot.leverage.ppm
New argument 'multiplot'.
o plot.anylist, plot.solist, plot.listof
New arguments panel.begin.args, panel.end.args
o influence.ppm, leverage.ppm, dfbetas.ppm
For Gibbs models, memory usage has been dramatically reduced,
so the code can handle larger datasets and finer quadrature schemes.
```

BUG FIXES

```
o Smooth.ppp
Results were incorrect when at='points' and leaveoneout=FALSE.
[Bug introduced in spatstat 1.20-5, October 2010.]
Fixed.
o funxy
Did not correctly handle one-line functions:
the resulting objects evaluated the wrong function in some cases.
[Spotted by Sebastian Meyer. Bug introduced in spatstat 1.45-0]
Fixed.
o mppm
Did not recognise the variable 'marks' in a formula.
Fixed.
o Smooth.ppp, bw.smoothppp
Crashed if X had two columns of marks and one column was constant.
[Bug introduced in spatstat 1.38-0, October 2014]
Fixed.
o Smooth.ppp
Results for 'at="points"' were garbled, for some values of 'sigma',
if X had more than one column of marks.
[Bug introduced in spatstat 1.38-0, October 2014]
Fixed.
o plot.layered
Crashed if one layer was a point pattern with several columns of marks.
Fixed.
o plot.ppm
Sometimes gave a spurious warning about a singular matrix.
Fixed.
o setminus.owin
Gave wrong or strange answer if the correct answer was empty.
Fixed.
o parameters.dppm
Crashed, due to a typo.
Fixed.
o progressreport
Crashed if n = 1.
Fixed.
CHANGES IN spatstat VERSION 1.45-2
```

OVERVIEW

```
o We thank Ottmar Cronie, Virginia Morera Pujol,
Sven Wagner and Marie-Colette van Lieshout for contributions.
o Recursive-partition point process models.
o Minkowski sum, morphological dilation and erosion with any shape.
o Important bug fix in spatial CDF tests.
o More bug fixes for replicated patterns.
o Simulate a model fitted to replicated point patterns.
o Inhomogeneous multitype F and G functions.
o Summary functions recognise correction="all"
o Leverage and influence code handles bigger datasets.
o More support for pixel images.
o Improved progress reports.
o New dataset 'redwood3'
o spatstat now Depends on the package 'rpart'
o Version nickname: 'Caretaker Mode'
```

NEW DATASETS

```
o redwood3
A more accurate version of the 'redwood' data.
```

NEW FUNCTIONS

```
o as.im.data.frame
Build a pixel image from a data frame of coordinates and pixel values.
o covering
Cover a window using discs of a given radius.
o dilationAny, erosionAny, %(-)%
Morphological dilation and erosion by any shape.
o FmultiInhom, GmultiInhom
Inhomogeneous multitype/marked versions of the summary functions Fest, Gest.
o kernel.moment
Moment or incomplete moment of smoothing kernel.
o MinkowskiSum, %(+)%
Minkowski sum of two windows: A %(+)% B, or MinkowskiSum(A,B)
o nobjects
New generic function for counting the number of 'things' in a dataset.
There are methods for ppp, ppx, psp, tess.
o parameters.interact, parameters.fii
Extract parameters from interpoint interactions.
[These existing functions are now documented.]
o ppmInfluence
Calculate leverage.ppm, influence.ppm and dfbetas.ppm efficiently.
o rppm, plot.rppm, predict.rppm, prune.rppm
Recursive-partition point process models
o simulate.mppm
Simulate a point process model fitted to replicated point patterns.
o update.interact
Update the parameters of an interpoint interaction.
[This existing function is now documented.]
o where.max, where.min
Find the spatial location(s) where a pixel image achieves its
maximum or minimum value.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o cdf.test.mppm
Now handles Gibbs models.
Now recognises covariate="x" or "y".
o leverage.ppm, influence.ppm, dfbetas.ppm
For Gibbs models, memory usage has been dramatically reduced,
so the code can handle larger datasets and finer quadrature schemes.
o plot.im
Now handles complex-valued images.
o connected.im
Now handles a logical-valued image properly.
o qqplot.ppm
Argument 'expr' can now be a list of point patterns,
or an envelope object containing a list of point patterns.
o as.layered
Default method now handles a (vanilla) list of spatial objects.
o summary functions
The argument 'correction="all"' is now recognised: it selects
all the available options.
This applies to Fest, F3est, Gest, Gcross, Gdot, Gmulti, G3est, Gfox,
Gcom, Gres, Hest, Jest, Jmulti, Jcross, Jdot, Jfox,
Kest, Kinhom, Kmulti, Kcross, Kdot, Kcom, Kres,
Kmulti.inhom, Kcross.inhom, Kdot.inhom, Kscaled, Ksector, Kmark,
K3est, Lscaled, markcorr, markcrosscorr,
nnorient, pairorient, pcfinhom, pcfcross.inhom, pcfcross, pcf, Tstat.
o clarkevans
The argument 'correction="all"' is now recognised: it selects
all the available options. [This is also the default.]
o predict.mppm
The argument 'type="all"' is now recognised: it selects
all the available options. [This is also the default.]
o plot.kppm
The argument 'what="all"' is now recognised: it selects
all the available options. [This is also the default.]
o connected.im, connected.owin
Arguments '...' now determine pixel resolution.
o anova.mppm
New argument 'fine'
o as.owin.data.frame
New argument 'step'
o discs
Now accepts a single numeric value for 'radii'.
o plot.ppp, plot.profilepl, plot.quadratcount, plot.quadrattest, plot.tess
Now recognise graphics parameters for text, such as 'family' and 'srt'
o as.function.tess
New argument 'values' specifies the function values.
o cdf.test
Calculations are more robust against numerical rounding effects.
o progressreport
Behaviour improved. New arguments 'tick', 'showtime'.
o simulate.ppm
New argument 'verbose'
o compileK, compilepcf
These internal functions are now documented.
```

BUG FIXES

```
o cdf.test.ppm
Calculation of p-values was incorrect for Gibbs models:
1-p was computed instead of p.
[Spotted by Sven Wagner.]
Fixed.
o subfits
The interaction coefficients of the submodels were incorrect
for Gibbs models with a multitype interaction (MultiStrauss, etc).
[Spotted by Sven Wagner.]
Fixed.
o subfits
Crashed when a Gibbs model included factor-valued spatial covariates
and not all levels of the factor were present in each row of the data.
[Spotted by Sven Wagner.]
Fixed.
o subfits
For Gibbs models with a multitype interaction (MultiStrauss, etc),
computation of the conditional intensity caused an error.
[Spotted by Sven Wagner.]
Fixed.
o diagnose.ppm
Crashed if what="smooth", when the original window was a rectangle.
[Spotted by Virginia Morera Pujol.]
Fixed.
o mppm
The x and y coordinates were not permitted in the
random-effects formula 'random'.
[Spotted by Sven Wagner.]
Fixed.
o vcov.ppm
The result had no 'dimnames', if the model was fitted using method="ho".
Fixed.
CHANGES IN spatstat VERSION 1.45-1
```

OVERVIEW

```
o This version was never released.
CHANGES IN spatstat VERSION 1.45-0
```

OVERVIEW

```
o We thank Monsuru Adepeju, Mario D'Antuono, Markus Herrmann,
Paul Hewson, Kassel Hingee, Greg McSwiggan, Suman Rakshit and Sven Wagner
for contributions.
o Important bug fix in leverage/influence diagnostics for Gibbs models.
o Numerous bug fixes in code for replicated point patterns.
o Surgery on linear networks.
o Tessellations on a linear network.
o Laslett's Transform.
o Colour maps for point patterns with continuous marks are easier to define.
o Pair correlation function estimates can be pooled.
o Stipulate a particular version of a package.
o Fixed namespace problems arising when spatstat is not loaded.
o Bug fixes and performance improvements.
o spatstat now contains 100,000 lines of R code.
o Version nickname: 'One Lakh'
```

NEW FUNCTIONS

```
o laslett
Laslett's Transform.
[Thanks to Kassel Hingee]
o lintess
Tessellation on a linear network.
o divide.linnet
Divide a linear network into pieces demarcated by a point pattern.
o insertVertices
Insert new vertices in a linear network.
o thinNetwork
Remove vertices and/or segments from a linear network etc
o connected.linnet
Find connected components of a linear network.
o nvertices, nvertices.linnet, nvertices.owin
Count the number of vertices in a linear network
or vertices of the boundary of a window.
o as.data.frame.linim, as.data.frame.linfun
Extract a data frame of spatial locations and function values
from an object of class 'linim' or 'linfun'.
o as.linfun, as.linfun.linim, as.linfun.lintess
Convert other kinds of data to a 'linfun' object.
o requireversion
Require a particular version of a package
(for use in stand-alone R scripts).
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o [.linnet, [.lpp
New argument 'snip' determines what to do with segments of the network
that cross the boundary of the window.
Default behaviour has changed.
o pcfinhom
Default behaviour is changed when 'lambda' is a fitted model.
The default is now to re-fit the model to the data before computing pcf.
New arguments 'update' and 'leaveoneout' control this.
o envelope methods
New argument 'funYargs' contains arguments to the summary function
when applied to the data pattern only.
o plot.ppp, plot.lpp
For a point pattern with continuous marks ('real numbers')
the colour arguments 'cols', 'fg', 'bg' can now be vectors of
colour values, and will be used to determine the default colour map
for the marks.
o symbolmap
Now accepts a vector of colour values for the arguments 'col', 'cols',
'fg', 'bg' if argument 'range' is given.
o closepairs.ppp, closepairs.pp3
New arguments 'distinct' and 'neat' allow more options.
o closepairs.ppp, closepairs.pp3
Argument 'ordered' has been replaced by 'twice'
(but 'ordered' is still accepted, with a warning).
o closepairs.ppp, closepairs.pp3
Performance improved (computation time and memory requirements reduced.)
This should improve the performance of many functions in spatstat.
o Geyer
The saturation parameter 'sat' can now be less than 1.
o lpp, as.lpp
These functions now handle the case where 'seg' and 'tp' are given
but 'x' and 'y' are missing.
o linnet
If the argument 'edges' is given, then this argument now determines the
ordering of the sequence of line segments. For example, the i-th row
of 'edges' specifies the i-th line segment in as.psp(L).
o funxy, distfun
The functions created by funxy and distfun have arguments (x,y).
The user may now give a ppp or lpp object for the argument 'x',
instead of giving two coordinate vectors 'x' and 'y'.
o crossing.psp
New argument 'details' gives more information about the intersections
between the segments.
o subset.ppp, subset.lpp, subset.pp3, subset.ppx
The argument 'subset' can now be any argument acceptable to the "[" method.
o density.lpp
New argument 'weights'.
o pcf.ppp
New argument 'ratio' allows several estimates of pcf to be pooled.
o summary.ppm
New argument 'fine' selects the algorithm for variance estimation.
o texturemap
Argument 'textures' can be missing or NULL.
o plot.lpp
New argument 'show.network'
o linnet
New argument 'warn'
o mppm
Performs more checks for consistency of the input data.
o mppm
New arguments 'gcontrol' and 'reltol.pql' control the fitting algorithm.
o edge.Trans
New argument 'gW' for efficiency.
o pool.fv
The default plot of the pooled function no longer includes
the variance curves.
o clickpoly
The polygon is now drawn progressively as the user clicks new vertices.
o Kest
Accelerated computation (for translation and rigid corrections)
when window is an irregular shape.
o vcov.ppm, leverage.ppm, influence.ppm, dfbetas.ppm
Performance slightly improved, for Gibbs models.
o Internal code
Performance slightly improved.
o Fest, Hest
Additional checks for errors in input data.
```

BUGS

o leverage.ppm, influence.ppm, parres.ppm, addvar.ppm Calculations were completely incorrect for Gibbs models, due to a coding error. Fixed.

o update.kppm If the call to 'update' did not include a formula argument or a point pattern argument, then all arguments were ignored. Example: update(fit, improve.type="quasi") was identical to 'fit'. Fixed.

o diagnose.ppm When applied to a model obtained from subfits(), in the default case (oldstyle=FALSE) the variance calculations were incorrect. Consequently the dotted lines representing significance bands were incorrect. An error or warning about negative variances occurred sometimes. However, calculations with oldstyle=TRUE were correct. The default has now been changed to oldstyle=TRUE for such models.

o [.lpp The local coordinate 'seg' was completely incorrect, when 'i' was a window. Fixed.

o leverage.ppm, influence.ppm, parres.ppm, addvar.ppm Crashed for Gibbs models in which the coefficient vector had length 1, such as the stationary Hardcore model. Fixed.

o subfits Crashed if the model included factor-valued spatial covariates. [Spotted by Sven Wagner] Fixed.

o subfits If the model included factor-valued spatial covariates, and if not all levels of the factor were present in each row of the data, the resulting objects were malformed and caused errors in other code. [Spotted by Sven Wagner] Fixed.

o subfits Crashed with some random-effects formulas. [Spotted by Sven Wagner] Fixed.

o improve.kppm An error message about a missing object 'gminus1' occurred when vcov=TRUE, fast.vcov=FALSE and type="clik1" or "wclik1". Fixed.

o plot.profilepl Failed with a message about a missing object 'finite'. Fixed.

o selfcut.psp Gave an error if marks(A) was a vector rather than a data frame. [Spotted by Paul Hewson.] Fixed.

o suffstat Gave an error for point process models with Geyer interaction. Fixed.

o nncross.lpp, distfun.lpp Crashed with obscure errors if Y consisted of a single point. Fixed.

o scan.test, scanmeasure Crashed sometimes with an error message from 'grow.mask'. Fixed.

o dppm Crashed sometimes with a message that the point pattern could not be found. [Scoping bug.] Fixed.

o mppm, profilepl Crashed, with a message about 'SpatstatVersion', if the 'spatstat' package was neither loaded nor attached. [Spotted by Markus Herrmann.] Fixed.

o qqplot.ppm Crashed sometimes when applied to a model obtained from subfits(). Fixed.

o anova.mppm Crashed sometimes with a message about mismatched coefficients. [Spotted by Sven Wagner.] Fixed.

o anova.mppm Crashed sometimes with a message about unrecognised option 'type="score"'. [Spotted by Sven Wagner.] Fixed.

o split.ppx Crashed if 'f' was not a factor. Fixed.

o idw The result was a pixel image defined in the rectangle Frame(X) instead of Window(X). Fixed.

o ppm Parameter estimates were slightly inaccurate when the model included the Geyer() interaction and the "isotropic" edge correction was used. Fixed.

o [.ppx Crashed if the number of points selected was less than 2. Fixed.

o linnet Crashed if there were no line segments at all. Fixed.

o kppm, improve.kppm Crashed if the model was stationary and improve.type != "none". Fixed.

o as.linim.default Did not correctly handle factor-valued data. Fixed.

o texturemap Crashed if no graphical arguments were specified. Fixed.

o vcov.mppm Ignored "..." arguments. Fixed.

o Kest If ratio=TRUE and correction=c('border', 'none') the result did not contain ratio information. Fixed.

o plot.ppp, plot.lpp Arguments 'chars' and 'cols' were ignored in some cases. Fixed.

o ppm Ignored argument 'emend'. Fixed.

o plot.dppm Gave warnings about unrecognised argument 'objectname'. Fixed.

o overlap.owin Sometimes returned a very small negative value, when the correct answer was 0. Fixed.

```
CHANGES IN spatstat VERSION 1.44-1
```

OVERVIEW

```
o We thank Brian Ripley for contributions.
o Urgent bug fix.
o More support for replicated point patterns.
o More support for tessellations.
o Version nickname: 'Gift Horse'
```

NEW FUNCTIONS

o as.function.tess Convert a tessellation to a function(x,y). The function value indicates which tile of the tessellation contains the point (x,y).

o tileindex Determine which tile of a tessellation contains a given point (x,y).

o persp.leverage.ppm Method for persp plots for objects of class leverage.ppm

o AIC.mppm, extractAIC.mppm AIC for point process models fitted to replicated point patterns.

o nobs.mppm, terms.mppm, getCall.mppm Methods for point process models fitted to replicated point patterns.

SIGNIFICANT USER-VISIBLE CHANGES

o anova.mppm Now handles Gibbs models, and performs the adjusted composite likelihood ratio test.

o update, step These functions now work for models of class 'mppm'.

o textureplot Argument x can now be something acceptable to as.im

o logLik.mppm New argument 'warn'.

BUGS

o nncross.lpp, nnwhich.lpp, distfun.lpp Caused a segmentation fault. [Spotted by Brian Ripley.] Fixed.

o anova.ppm If a single 'object' was given, and the object was a Gibbs model, then 'adjust' was effectively set to FALSE. Fixed.

```
CHANGES IN spatstat VERSION 1.44-0
```

OVERVIEW

o We thank Jonas Geldmann, Andrew Hardegen, Kassel Hingee, Tom Lawrence, Robin Milne, Gopalan Nair, Suman Rakshit, Peijian Shi and Rasmus Waagepetersen for contributions.

o More support for multidimensional point patterns and point processes.

o More options for envelopes and related Monte Carlo tests.

o More support for model comparison.

o k-th nearest neighbours on a linear network.

o Penttinen process can be simulated (by Metropolis-Hastings or CFTP).

o Calculate the predicted variance of number of points.

o Convexifying operation for sets.

o Subdivide a linear network.

o Accelerated algorithms for linear networks.

o Quadrat counting accelerated, in some cases.

o Version nickname: 'The Sound of One Hand Typing'

NEW FUNCTIONS

o rPenttinen Simulate the Penttinen process using perfect simulation.

o varcount Given a point process model, compute the predicted variance of the number of points falling in a window.

o inside.boxx Test whether multidimensional points lie inside a specified multidimensional box.

o lixellate Divide each segment of a linear network into smaller segments.

o nsegments.linnet, nsegments.lpp Count the number of line segments in a linear network.

o grow.boxx Expand a multidimensional box.

o deviance.ppm, deviance.lppm Deviance for a fitted point process model.

o pseudoR2 Pseudo-R-squared for a fitted point process model.

o tiles.empty Checks whether each tile of a tessellation is empty or nonempty.

o summary.linim Summary for a pixel image on a linear network.

SIGNIFICANT USER-VISIBLE CHANGES

o rMaternI, rMaternII These functions can now generate random patterns in three dimensions and higher dimensions, when the argument 'win' is of class 'box3' or 'boxx'.

o "[.ppx" The subset index 'i' may now be a spatial domain of class 'boxx' or 'box3'.

o rmh.ppm, rmhmodel.ppm, simulate.ppm A model fitted using the 'Penttinen' interaction can now be simulated.

o rmh.default, rmhmodel.default These functions now recognise cif='penttinen' for the Penttinen interaction.

o envelope New argument 'clamp' gives greater control over one-sided envelopes.

o dclf.test, mad.test, dclf.progress, mad.progress, dclf.sigtrace, mad.sigtrace New argument 'clamp' determines the test statistic for one-sided tests.

o dclf.progress, mad.progress, dclf.sigtrace, mad.sigtrace, mctest.progress, mctest.sigtrace, dg.progress, dg.sigtrace New argument 'rmin' determines the left endpoint of the test interval.

o dclf.test, mad.test, dg.test, dg.progress, dg.sigtrace, dg.envelope (also accepted by dclf.progress, mad.progress, dclf.sigtrace, mad.sigtrace) New argument 'leaveout' specifies how to calculate the deviation between the observed summary function and nominal reference value.

o envelope New argument 'funargs'

o Hest Argument X can now be a pixel image with logical values. New argument 'W'. [Based on code by Kassel Hingee.]

o nncross.lpp, distfun.lpp New argument 'k' allows calculation of k-th nearest neighbour. Computation accelerated.

o logLik.ppm New argument 'absolute'.

o plot.kppm New arguments 'pause' and 'xname'.

o tess Argument 'window' is ignored when xgrid, ygrid are given.

o as.polygonal Can now repair errors in polygon data, if repair=TRUE.

o rStrauss, rHardcore, rStraussHard, rDiggleGratton, rDGS, rPenttinen New argument 'drop'.

o Kest.fft Now has '...' arguments allowing control of spatial resolution.

o lppm Computation accelerated.

o quadratcount.ppp Computation accelerated in some cases.

o dg.test Computation accelerated.

BUGS

o runifpointx, rpoisppx Crashed if nsim > 1. Fixed.

o triangulate.owin Results were incorrect in some special cases. Fixed.

o quadrat.test, clarkevans.test In rare cases, the computed Monte Carlo p-value could have been greater than 1. This could have occurred only when nsim was an even number and when the correct p-value was equal to 1. Fixed.

o linearmarkequal Result was a data frame instead of an 'fv' object. Fixed.

o point-in-polygon test The function inside.owin could take a very long time to check whether points are inside a polygonal window, if the coordinates were very large numbers. This was due to numerical overflow. (Fixed??)

o as.fv.kppm Crashed if the model was not fitted by minimum contrast. Fixed.

o plot.fv Crashed in some obscure cases. Fixed.

o collapse.fv Did not allow 'same=NULL'. Fixed.

o dclf.progress, mad.progress, dg.progress, dclf.sigtrace, mad.sigtrace, dg.sigtrace The results could not be re-plotted using a plot formula, because the internal data were slightly corrupted. Fixed.

o Kest.fft Result was incorrectly normalised. Fixed.

o crosspairs If X and Y were identical point patterns, the result was not necessarily symmetric (on some machines) due to numerical artifacts. Fixed.

o plot.fv Lines were not correctly clipped to the plot region when 'ylim' was given. Fixed.

o pool.envelope The 'scale' argument was not handled correctly. Fixed.

```
CHANGES IN spatstat VERSION 1.43-0
```

OVERVIEW

o We thank Leanne Bischof, Christophe Biscio, Belarmain Fandohan, Andrew Hardegen, Frederic Lavancier, Tom Lawrence, Martin Maechler, Greg McSwiggan, Robin Milne, Gopalan Nair, Tuomas Rajala, Suman Rakshit, Ben Ramage, Francois Semecurbe and Ida-Maria Sintorn for contributions.

o spatstat now depends on the package 'nlme'.

o spatstat now depends on R 3.2.2 or later.

o Simulation algorithms have been accelerated; simulation outcomes
are *not* identical to those obtained from previous versions of spatstat.

o Determinantal point process models.

o Random-effects and mixed-effects models for replicated patterns.

o Dao-Genton test, and corresponding simulation envelopes.

o Simulated annealing and simulated tempering.

o spatstat colour tools now handle transparent colours.

o Improvements to "[" and subset() methods

o Extensions to kernel smoothing on a linear network.

o Support for one-dimensional smoothing kernels.

o Bug fix in Metropolis-Hastings simulation.

o Mark correlation function may include weights.

o Cross-correlation version of the mark correlation function.

o Variance calculations for replicated patterns.

o Penttinen pairwise interaction model.

o Contour plots with colours determined by a colour map.

o New dataset: Australian states and territories.

o More support for multi-dimensional point patterns.

o Minor improvements and bug fixes.

o Version nickname: "Mixed Effects"

NEW DATASET

o austates The states and large mainland territories of Australia represented as polygonal regions forming a tessellation.

NEW FUNCTIONS

o dppm Fit a determinantal point process model to point pattern data.

o fitted.dppm, predict.dppm, intensity.dppm Predict a fitted dppm object.

o logLik.dppm, AIC.dppm, extractAIC.dppm, nobs.dppm Likelihood and AIC for determinantal point process models (enabling the use of 'step')

o coef.dppm, formula.dppm, print.dppm, terms.dppm, labels.dppm, model.frame.dppm, model.matrix.dppm, model.images.dppm, is.stationary.dppm, reach.dppm, unitname.dppm, unitname<-.dppm, Window.dppm Various methods for dppm objects.

o parameters.dppm Extract meaningful list of model parameters

o objsurf.dppm Objective function surface of a dppm object

o residuals.dppm Residual measure for a dppm object.

o dppBessel, dppCauchy, dppGauss, dppMatern, dppPowerExp Determinantal Point Process models.

o update.dppmodel

Set parameter values in a dpp model.

o is.stationary.dppmodel, print.dppmodel, reach.dppmodel, valid.dppmodel

Basic information about a dpp model

o rdpp, simulate.dppmodel Simulation of a dpp model.

o intensity.dppmodel, Kmodel.dppmodel, pcfmodel.dppmodel Moments of a dpp model

o dim.dppmodel, dppapproxkernel, dppapproxpcf, dppeigen, dppfamily, dppkernel, dppparbounds, dppspecdenrange, dppspecden Helper functions for dpp models.

o dclf.sigtrace, mad.sigtrace, mctest.sigtrace Significance trace of Monte Carlo test

o dg.test Dao-Genton adjusted Monte Carlo goodness-of-fit test.

o dg.envelope Simulation envelopes corresponding to Dao-Genton test.

o dg.sigtrace Significance trace for Dao-Genton test

o dg.progress Progress plot for Dao-Genton test

o markcrosscorr Mark cross-correlation function for point patterns with several columns of marks

o fixef.mppm, ranef.mppm Extract fixed effects and random effects from a point process model fitted to replicated point patterns.

o rtemper Simulated annealing or simulated tempering.

o to.opaque, to.transparent Change transparency value in colours

o rgb2hsva Convert RGB to HSV data, like rgb2hsv, but preserving transparency.

o superimpose.ppplist, superimpose.splitppp New methods for 'superimpose' for lists of point patterns.

o dkernel, pkernel, qkernel, rkernel Probability density, cumulative probability, quantiles and random generation from distributions used in basic one-dimensional kernel smoothing.

o kernel.factor Auxiliary calculations for one-dimensional kernel smoothing.

o PPversion, QQversion Transformation of a summary function to its P-P or Q-Q counterpart.

o spatdim Spatial dimension of any object in the spatstat package.

o as.boxx Convert data to a multi-dimensional box.

o intensity.ppx Method for 'intensity' for multi-dimensional space-time point patterns.

o fourierbasis Evaluate Fourier basis functions in any number of dimensions.

o valid New generic function, with methods valid.ppm, valid.lppm, valid.dppmodel

o emend, emend.ppm, emend.lppm New generic function with methods for ppm and lppm. emend.ppm is equivalent to project.ppm

o Penttinen New pairwise interaction model.

o quantile.density Calculates quantiles from kernel density estimates.

o CDF.density Calculates cumulative distribution function from kernel density estimates.

SIGNIFICANT USER-VISIBLE CHANGES

o simulation Several basic simulation algorithms have been accelerated. Consequently, simulation outcomes are not identical to those obtained with previous versions of spatstat, even when the same random seed is used. To ensure compatibility with previous versions of spatstat, revert to the slower code by setting spatstat.options(fastthin=FALSE, fastpois=FALSE).

o mppm Now handles models with a random effect component. New argument 'random' is a formula specifying the random effect.

o vcov.mppm Now handles models with Gibbs interactions.

o [.ppp New argument 'clip' determines whether the window is clipped.

o [.ppp The previously-unused argument 'drop' now determines whether to remove unused levels of a factor.

o [.pp3, [.lpp, [.ppx, subset.ppp, subset.pp3, subset.lpp, subset.ppx These methods now have an argument 'drop' which determines whether to remove unused levels of a factor.

o density.lpp Now supports both the 'equal-split continuous' and 'equal-split discontinuous' smoothers. New argument 'continuous' determines the choice of smoother.

o envelope New argument 'scale' allows global envelopes to have width proportional to a specified function of r, rather than constant width.

o dclf.test, mad.test, dclf.progress, mad.progress, mctest.progress New argument 'scale' allows summary function values to be rescaled before the comparison is performed.

o dclf.test, mad.test New argument 'interpolate' supports interpolation of p-value.

o dclf.progress, mad.progress, mctest.progress New argument 'interpolate' supports interpolation of critical value of test.

o simulate.ppm New argument 'w' controls the window of the simulated patterns.

o default.rmhcontrol, default.rmhexpand New argument 'w'.

o markcorr New argument 'weights' allows computation of the weighted version of the mark correlation function.

o density.lpp New argument 'kernel' specifies the smoothing kernel. Any of the standard one-dimensional smoothing kernels can be used.

o contour.im New argument 'col' specifies the colour of the contour lines. If 'col' is a colour map, then the contours are drawn in different colours.

o plot.ppp The default colour for the points is now a transparent grey, if this is supported by the plot device.

o rgbim, hsvim New argument 'A' controls the alpha (transparency) channel.

o rgb2hex, col2hex, paletteindex, is.colour, samecolour, complementarycolour, is.grey, to.grey These colour tools now handle transparent colours.

o rgb2hex New argument 'maxColorValue'

o to.grey New argument 'transparent'.

o progressreport New argument 'state' New option: style="tk"

o rLGCP This function no longer requires the package 'RandomFields' to be loaded explicitly.

o kppm Fitting a model with clusters="LGCP" no longer requires the package 'RandomFields' to be loaded explicitly.

o rpoispp Accelerated, when 'lambda' is a pixel image.

o rthin Accelerated, when 'P' is a single number.

o spatstat.options New options 'fastthin' and 'fastpois' enable fast simulation algorithms. Set these options to FALSE to reproduce results obtained with previous versions of spatstat.

o split.ppp The splitting variable 'f' can now be a logical vector.

o collapse.fv This is now treated as a method for the 'nlme' generic 'collapse'. Its syntax has been adjusted slightly.

o diagnose.ppm, plot.diagppm New arguments col.neg, col.smooth control the colour maps.

o valid.ppm This is now a method for the generic function 'valid'.

o ppm.ppp, ppm.quad New argument 'emend', equivalent to 'project'.

o "[<-.im" Accepts an array for 'value'.

o as.im.function New argument 'strict'.

o bw.ppl New argument 'weights'.

o plot.mppm New argument 'se'.

o dclf.test, mad.test Formal arguments 'use.theo' and 'internal' have been removed.

o predict.kppm, residuals.kppm Now issues a warning when the calculation ignores the cluster/Cox component and treats the model as if it were Poisson. (This currently happens in predict.kppm when se=TRUE or interval != "none", and in residuals.kppm when type != "raw").

BUG FIXES

o lpp Crashed if X was a 4-column matrix. Fixed.

o plot.fv Crashed with some graphics devices, if legend=TRUE. Fixed.

o effectfun Crashed if 'covname' was missing. Fixed.

o rVarGamma, rMatClust, rThomas, rCauchy, rNeymanScott Crashed if 'kappa' was a function or image instead of a single number. [Spotted by Ben Ramage.] Fixed.

o plot.mppm Crashed with a message about "figure margins too large" unless the argument se=FALSE was given explicitly. Fixed.

o opening.owin, closing.owin Crashed sometimes, with a message about a rectangle not containing a window. Fixed.

o persp.im Crashed if all pixel values were equal to zero (unless zlim was given). Fixed.

o predict.ppm Crashed sometimes if the model was fitted with use.gam=TRUE.

o as.linim.linfun Generated an error ('L must be a linear network') if extra arguments were given.

o as.function.fv Generated an error when executed in the 'covr' package. Fixed.

o rmh, simulate.ppm Results were incorrect for inhomogeneous multitype models simulated with fixall=TRUE (i.e. prescribing a fixed number of points of each type) if the model was segregated (i.e. if different types of points had different first order trend). Fixed.

o dclf.progress, mad.progress Ignored the argument 'alternative'. Fixed.

o $<-.hyperframe, [<-.hyperframe Result was garbled if 'value' was a hyperframe with one column.

o rmh.ppm Argument 'w' was ignored in some cases. Fixed.

o Hest There was an artefact at r=0 when conditional=TRUE. Fixed.

o [.msr The result of M[W] where W is a window was a measure with window W, instead of intersect.owin(W, Window(M)). Fixed.

o pool.envelope Did not always respect the value of 'use.theory'. Fixed.

o envelope, pool.envelope If 'ginterval' was given, the results were in a slightly incorrect format. Fixed.

o pool.envelope Did not check for compatible values of 'ginterval'. Fixed.

```
CHANGES IN spatstat VERSION 1.42-2
```

OVERVIEW

o We thank Bob Klaver and Harold-Jeffrey Ship for contributions.

o Improvements to simulation of Neyman-Scott processes.

o Improvements to fitting of Neyman-Scott models.

o Extended functionality for pixel images.

o Fitted intensity on linear network

o Triangulation of windows.

o Corrected an edge correction.

o Bug fixes and performance improvements.

o Nickname: 'Barking at Balloons'

NEW FUNCTIONS

o triangulate.owin Decompose a spatial window into triangles.

o fitted.lppm Fitted intensity values for a point process on a linear network.

SIGNIFICANT USER-VISIBLE CHANGES

o rThomas, rMatClust, rCauchy, rVarGamma When the model is approximately Poisson, it is simulated using rpoispp. This avoids computations which would require huge amounts of memory. New argument 'poisthresh' controls this behaviour.

o update.kppm Now handles additional arguments in any order, with or without names. Changed arguments. Improved behaviour.

o kppm, clusterfit New argument 'algorithm' specifies the choice of optimisation algorithm.

o kppm Left hand side of formula can now involve entries in the list 'data'.

o rotmean New argument 'padzero'. Default behaviour has changed.

o rose.default New argument 'weights'.

o rose New arguments 'start' and 'clockwise' specify the convention for measuring and plotting angles.

o padimage New argument 'W' allows an image to be padded out to fill any window.

o union.owin Improved behaviour when there are more than 2 windows.

o clusterset Improved behaviour.

o affine.owin Allows transformation matrix to be singular, if the window is polygonal.

BUG FIXES

o spatstat spatstat could not be installed on some 64-bit VM systems because of an apparent bug in R. Fixed.

o rThomas, rMatClust, rCauchy, rVarGamma Large values of the scale parameter could cause the algorithm to freeze or require huge amounts of memory. Fixed.

o pcf, pcfinhom Crashed if the point pattern was empty. Fixed.

o plot.fv Gave an error message if all 'y' values were equal, when legend=TRUE. Fixed.

o rose.default Display was incorrect when unit="radian". Fixed.

o Kest Ohser-Stoyan rigid motion correction (correction='rigid') was calculated incorrectly at large distances. Fixed.

o summary.im Issued a warning about numerical overflow in some cases. [Spotted by Bob Klaver.] Fixed.

o plot.im Sometimes warned that 'box' is not a graphical parameter. Fixed.

```
CHANGES IN spatstat VERSION 1.42-1
```

OVERVIEW

o We thank Andrew Hardegen, Tom Lawrence, Robin Milne, Suman Rakshit, and Brian Ripley for contributions.

o Urgent bug fix.

o More robust simulation of cluster processes.

o Slightly accelerated.

o Version nickname: 'Vogon Poetry'

NEW FUNCTIONS

o boundingbox.solist Method for boundingbox for lists of spatial objects.

SIGNIFICANT USER-VISIBLE CHANGES

o rThomas, rMatClust, rCauchy, rVarGamma, rNeymanScott New faster algorithm which is more robust against extreme values of the parameters.

o rNeymanScott New argument 'nonempty' controls choice of algorithm.

o solist, as.solist Accelerated.

o as.list.hyperframe Accelerated.

BUG FIXES

o residuals.mppm Brought some computers to a grinding halt, due to the bug in solist(). Fixed.

o solist, as.solist In rare cases, the format was corrupted, or the algorithm never terminated. Fixed.

```
CHANGES IN spatstat VERSION 1.42-0
```

OVERVIEW

o We thank Anders Bilgrau, Ute Hahn, Jack Hywood, Tuomas Rajala, Cody Schank, Olivia Semboli and Ben Taylor for contributions.

o Version nickname: 'Life, The Universe and Everything'

o Permutation test for difference between groups of point patterns.

o Variational Bayes estimation for point process models.

o Score test in anova.ppm

o ROC curve, and discrimination index AUC, for fitted models.

o Interactive text editor for spatial datasets.

o Tools for analysing data on a tree.

o Kernel density/intensity estimation on a linear network.

o Random pixel noise.

o Improved behaviour of polygon geometry operations.

o Improved support for cluster and Cox models.

o Improved basic support for owin objects.

o Improved support for tessellations.

o More hierarchical Gibbs interactions.

o Modifications to Kest.

o summary method for Cox and cluster models.

o class 'listof' is almost completely replaced by 'anylist' and 'solist'.

o Improvements and bug fixes.

o spatstat now depends on R version 3.2.0 or later.

NEW FUNCTIONS

o studpermu.test Studentised permutation test for difference between groups of point patterns. Generously contributed by Ute Hahn.

o AIC.kppm, extractAIC.kppm, logLik.kppm, nobs.kppm Methods for computing AIC for fitted Cox and cluster models.

o transmat Convert pixel arrays between different display conventions.

o roc Receiver Operating Characteristic curve.

o auc Discrimination index AUC (area under the ROC curve)

o edit.ppp, edit.psp, edit.im Interactive text editor works for spatial datasets.

o edit.hyperframe Interactive text editor works for hyperframes.

o parameters Extract all parameters from a fitted model.

o density.lpp Kernel estimation of point process intensity on a linear network.

o extractbranch, deletebranch, treeprune, treebranchlabels, begins Tools for analysing data on a tree.

o rnoise Random pixel noise.

o as.data.frame.owin Convert a window to a data frame.

o harmonise.owin Convert several binary mask windows to a common pixel grid.

o copyExampleFiles Copy the raw data files from an installed dataset to a chosen folder, for use in a practice exercise.

o density.ppplist Method for 'density' for lists of point patterns.

o inradius Radius of largest circle inside a window.

o mergeLevels Merge different levels of a factor.

o relevel.im, relevel.ppp, relevel.ppx Change the reference level of a factor.

o simulate.profilepl simulation method for models fitted by profile maximum pseudolikelihood.

o predict.rho2hat Prediction method for class rho2hat

o with.msr Evaluate (an expression involving) components of a measure.

o summary.kppm, print.summary.kppm, coef.summary.kppm Methods for 'summary' and 'coef(summary(..))' for Cox and cluster models.

o as.im.funxy Method for as.im for class funxy.

o shift.linim, scalardilate.linim, affine.linim Geometrical transformations for 'linim' objects.

o Smooth.solist Smooth method for a list of spatial objects.

o unitname.tess, unitname<-.tess Tessellations now keep track of the name of the unit of length.

o dirichletAreas Faster algorithm for tile.areas(dirichlet(X)).

o identify.lpp Method for 'identify' for point patterns on a linear network.

o HierStraussHard, HierHard Hierarchical interactions for Gibbs models.

o delaunayDistance, delaunayNetwork, dirichletEdges, dirichletNetwork, dirichletVertices, dirichletWeights These functions will replace delaunay.distance, delaunay.network, dirichlet.edges, dirichlet.network, dirichlet.vertices and dirichlet.weights respectively. The latter are now 'deprecated'.

SIGNIFICANT USER-VISIBLE CHANGES

o ppm Now supports Variational Bayes fitting method.

o kppm 'AIC' and 'step' now work for kppm objects fitted using maximum Palm likelihood.

o kppm The default for the weight function 'weightfun' has been changed, for better performance.

o envelope envelope methods now have argument 'use.theory' specifying whether to use the 'theoretical' value of the summary function when constructing simultaneous envelopes.

o anova.ppm Now performs the Score Test, for Poisson models only, if argument test="Rao" or test="score".

o Kest New argument 'rmax' controls maximum value of argument 'r'

o diagnose.ppm Now computes and prints the null standard deviation of the smoothed Pearson residual field, when appropriate.

o nncorr, nnmean, nnvario New argument 'k' specifies k-th nearest neighbour.

o quadrat.test.ppp, quadrat.test.quadratcount New argument 'lambda' supports a test of the Poisson process with given intensity 'lambda'.

o clickpoly, clickbox These functions now handle graphical arguments to polygon() when drawing the resulting polygon or rectangle.

o owin, as.owin, as.mask owin(mask=D) or as.owin(D) or as.mask(D) will produce a binary mask window if D is a data frame with two columns of (x,y) coordinates or a data frame with three columns containing (x,y,logical).

o as.owin.data.frame W can now be a data frame with only two columns, giving the spatial coordinates of the pixels that are inside the window.

o rose Tick marks now have labels showing the angle (in degrees or radians).

o distcdf New argument 'regularise' determines whether values at short distances will be smoothed to avoid discretisation artefacts.

o rpoislinetess Return value now has an attribute 'lines' giving the realisation of the Poisson line process.

o intersect.owin, union.owin, setminus.owin New argument 'p' controls resolution of polygon clipping algorithm.

o intersect.owin, union.owin Arguments may be lists of windows, of class 'solist'. Formal arguments A and B have been removed.

o superimpose Now handles lists of point patterns (objects of class 'ppplist' or 'splitppp')

o density.ppp New argument 'positive' allows the user to stipulate that density values must be positive (avoiding numerical errors which occasionally produce small negative values).

o adaptive.density Now accepts f = 0 (uniform intensity estimate) and f = 1 (Voronoi intensity estimate) as well as 0 < f < 1. Algorithm accelerated.

o rSSI Can now generate inhomogeneous patterns.

o effectfun Now works for 'kppm' and 'lppm' objects as well.

o integral.im, integral.msr Argument 'domain' can now be a tessellation; the integral over each tile of the tessellation is returned.

o allstats, compareFit, markcorr, split.ppx, by.ppp Result is now of class 'anylist'.

o by.im, density.splitppp, idw, model.images, nnmark, pixellate.ppp, predict.lppm, predict.ppm, quadratcount.splitppp, quadratresample, relrisk, Smooth.msr, split.im, tiles Result is now of class 'solist'.

o split.ppp New argument 'reduce'. Result now inherits class 'ppplist' and 'solist', as well as 'splitppp'

o rLGCP New argument 'nsim' allows multiple patterns to be generated.

o alltypes New argument 'reuse' determines whether all simulation envelopes are based on the same set of simulated patterns, or on independent sets.

o rpoispp, runifpoint New argument 'ex' makes it possible to generate a random pattern similar to an example point pattern.

o effectfun Argument 'covname' is not needed if the model has only one covariate.

o quadratcount Argument 'tess' can now be anything acceptable to as.tess.

o tess New argument 'unitname' specifies the name of the unit of length. If it is missing, unitname information will be extracted from the other data.

o intersect.tess, chop.tess, quadrats Results of these functions now have the same 'unitname' as their input.

o persp.im, nnclean, plot.qqppm, plot.bw.optim These plotting functions now obey spatstat.options('monochrome')

o lurking Now returns an object of class 'lurk' which has a plot method. Two-standard-deviation limits are now plotted using grey shading.

o marktable
New argument 'N' for studying the N nearest neighbours.

New argument 'collapse' for manipulating the contingency table.

o harmonise.fv Now discards columns with names which do not match.

o eval.fv New argument 'equiv' can be used to declare that two columns with different names in different objects are equivalent.

o quantile.ewcdf New argument 'type' controls the type of quantile.

o plot.imlist New argument 'plotcommand' specifies how to plot each image.

o persp.im The lower extent of the apron can now be controlled by 'zlim'.

o quadscheme Argument 'method' is partially matched.

o Kdot, Ldot New argument 'from' is an alternative to 'i'.

o Kcross, Lcross New arguments 'from' and 'to' are alternatives to 'i' and 'j' respectively.

o varblock Changed the ordering (and therefore default colours/styles) of curves in the plot, to match other functions like lohboot.

o bw.diggle New argument 'nr' controls accuracy.

o textureplot Now accepts a pixel image, a tessellation, or anything acceptable to as.tess.

o textureplot Line spacing in legend now matches line spacing in main display.

o [.tess Subset index can now be a window.

o plot.tess Can now plot a text label in each tile.

o plot.tess New argument 'do.plot'.

o MultiHard, MultiStrauss, MultiStraussHard, HierStrauss Printed output of fitted model now respects spatstat.options('terse').

o print.ppm Reduced redundancy in output in some cases.

o print.msr Responds better to spatstat.options('terse').

o print.ppm, print.fii, print.interact Irregular parameters are now printed to the number of significant figures specified by options("digits").

o square New argument 'unitname'.

o plot.fv Return value is now invisible.

o delaunay.distance, delaunay.network, dirichlet.edges, dirichlet.network, dirichlet.vertices These functions are now 'deprecated', and will be replaced by delaunayDistance, delaunayNetwork, dirichletEdges, dirichletNetwork and dirichletVertices respectively.

o data(residualspaper) In the real datasets (Fig1 and Fig11), the name of the unit of length has now been recorded.

o rLGCP This function now requires the package 'RandomFields' to be loaded explicitly by library(RandomFields) or require(RandomFields), unless model="exp".

o iplot, istat These functions now require the package 'rpanel' to be loaded explicitly by library(rpanel) or require(rpanel).

o ppm, quadscheme Improved calculation of Dirichlet weights.

o countends New argument 'toler' controls numerical errors

o diagnose.ppm Improved handling of additional graphics arguments.

o pcf3est Mathematical labels changed.

o plot.hyperframe Default margin spacing has been increased.

BUG FIXES

o Kinhom, Linhom The value of 'theo' was erroneously rescaled by a small amount, when renormalise=TRUE (the default). Fixed.

o Kmark Values were erroneously rescaled. Fixed.

o union.owin Strange results were sometimes obtained when taking the union of more than two windows. Fixed.

o rpoispp3 Implementation was incorrect for nsim > 1. (Results may have been incorrect.) Spotted by Jack Hywood. Fixed.

o as.owin.data.frame Crashed if the window was not connected. Fixed.

o Frame<- Crashed when applied to a binary mask. Fixed.

o rho2hat Crashed if cov1="x" and cov2="y". Fixed.

o as.mask Crashed sometimes when only the argument 'xy' was given. Fixed.

o ppm Crashed (rarely) when method='ho' if the simulated pattern was empty. Fixed.

o istat, iplot Crashed in recent versions of rpanel. Fixed.

o convexhull Crashed if applied to a 'psp' object. Fixed.

o plot.ppm Crashed with message about 'variable lengths differ'. Fixed.

o plot.solist Crashed when applied to a list of point patterns if some patterns had more than one column of marks. Fixed.

o Smooth.ppp Crashed if applied to a point pattern with several columns of marks if some of the columns were factors. Fixed.

o runifpoint3, rpoispp3 Crashed if nsim > 1. Spotted by Jack Hywood. Fixed.

o hist.im Crashed if argument 'freq' was given. Fixed.

o MultiStraussHard Generated misleading error messages (e.g. 'model is invalid') when arguments 'iradii' and 'hradii' did not have the same pattern of NA's. Fixed.

o plot.solist Figures were sometimes aligned incorrectly when the argument 'panel.args' was given. Fixed.

o scaletointerval Results sometimes fell slightly outside the desired interval due to numerical error. Fixed.

o plot.solist Behaved incorrectly when plotcommand='persp'. Fixed.

o "[.hyperframe" Sometimes returned an 'anylist' when it should have returned a 'solist'. Fixed.

o plot.im Did not plot surrounding frame box when ribbon=FALSE. Fixed.

o envelope The functions stored when savefuns=TRUE did not inherit the correct name for the unit of length. Fixed.

o print.ppm, print.fii, print.interact Layout was misaligned. Fixed.

o plot.plotppm Paused for input when it was not appropriate. Fixed.

o plot.fv On png devices, the legend box was drawn with a white background, obscuring the main plot. Fixed.

o plot.owin, plot.ppp, plot.im There was unnecessary extra space above the main title. Fixed.

o plot.rho2hat Colour map ribbon was drawn but not annotated. Fixed.

o density.splitppp, density.ppplist Format was out of order if se=TRUE. Fixed.

o MultiStraussHard project.ppm sometimes yielded a model that was still invalid. Fixed.

```
CHANGES IN spatstat VERSION 1.41-1
```

OVERVIEW

o This is identical to the major release 1.41-0 except for minor bug fixes. The change log for 1.41-0 is repeated here with minor modifications.

o Version nickname: 'Ides of March'

o We thank Ahmed El-Gabbas, Ute Hahn, Aruna Jammalamadaka, Ian Renner, Brian Ripley, Torben Tvedebrink and Sasha Voss for contributions.

o Fixed a bug causing a segmentation fault.

o Standard errors for kernel estimates of intensity.

o Test for segregation.

o Tessellations may now have marks.

o Nested splitting.

o More support for cluster models. Reorganised parametrisation.

o Sparse data representation of linear networks.

o More support for data on a linear network.

o New datasets: 'spiders' and 'dendrite'.

o Improvements and bug fixes.

o spatstat no longer uses Fortran.

o spatstat no longer depends on the package 'scatterplot3d'.

o spatstat now imports (rather than 'suggests') the Matrix package.

NEW DATASETS

o dendrite Dendritic spines on the dendrite network of a neuron. A point pattern on a linear network. Generously contributed by Aruna Jammalamadaka.

o spiders Spider webs on the mortar lines of a brick wall. A point pattern on a linear network. Generously contributed by Sasha Voss.

NEW FUNCTIONS

o segregation.test Test of spatial segregation of types in a multitype point pattern.

o clusterfield, clusterkernel Compute the cluster kernel (offspring density) of a cluster process model, or compute the cluster field generated by superimposing copies of the cluster kernel at specified locations.

o clusterradius Compute the radius of the support of the offspring density of a cluster process model.

o as.linnet.psp Convert a line segment pattern to a linear network by guessing the connectivity using a distance threshold.

o iplot.linnet, iplot.lpp Methods for interactive plotting 'iplot' for objects of class lpp and linnet.

o Mathematical operations are now supported for pixel images on a linear network. See help(Math.linim)

o dirichlet.network, delaunay.network The linear networks formed by the Dirichlet tessellation and Delaunay triangulation.

o dirichlet.edges The edges of the Dirichlet tessellation.

o selfcut.psp Cut line segments where they cross each other.

o vertices.linnet Extract the vertices (nodes) of the linear network.

o vertexdegree Compute the degree of each vertex in a linear network.

o pixellate.linnet Pixellate a linear network.

o subset.hyperframe 'subset' method for class 'hyperframe'.

o head.hyperframe, tail.hyperframe 'head' and 'tail' methods for hyperframes.

o clickdist Measures the distance between two spatial locations clicked by the user.

o solapply, anylapply wrappers for 'lapply' which return a list of class 'solist' or 'anylist'.

o Kmark Weighted K-function. Identical to 'markcorrint' and will eventually replace it.

o marks.tess, marks<-.tess, unmark.tess: Extract or change the marks associated with the tiles of a tessellation.

o quantess Quantile tessellation: divide space into pieces which contain equal amounts of 'stuff'.

o nestsplit Nested split

o integral New generic function for integrating functions, with methods for 'im', 'msr', 'linim' and 'linfun'.

o selfcut.psp Cut line segments where they cross each other

o as.function.im Convert a pixel image to a function(x,y).

o as.linnet.linim Extract the linear network from a 'linim' object.

o pool.fv, pool.anylist New methods for 'pool'

o Window.linnet Extract the two-dimensional window containing a linear network.

SIGNIFICANT USER-VISIBLE CHANGES

o linnet, lpp A linear network can now be built in 'sparse matrix' form which requires much less memory.

o chicago The Chicago street crimes data are now stored in 'sparse matrix' form. To convert them to non-sparse form, use as.lpp(chicago, sparse=FALSE)

o kppm The parametrisation of cluster models has been reorganised. The scale parameter is now always called 'scale'. Results should be backward-compatible.

o cauchy.estK, cauchy.estpcf, matclust.estK, matclust.estpcf, thomas.estK, thomas.estpcf, vargamma.estK, vargamma.estpcf The parametrisation of cluster models has been reorganised. The scale parameter is now always called 'scale'.

o plot.kppm Also plots the cluster kernel.

o density.ppp New argument 'se' allows calculation of standard errors as well.

o plot.pp3 Now produces a genuine perspective view. New arguments control the eye position for the perspective view.

o Emark, Vmark These functions can now work with multiple columns of marks.

o pixellate.psp Can now count the number of segments that intersect each pixel, instead of the total length of intersection.

o linfun If g = linfun(f, L), the function f will always be called as f(x,y,seg,tp, ...) It is no longer expected to handle the case where 'seg' and 'tp' are absent. The resulting function g can now be called as g(X) where X is an lpp object, or as g(x,y) or g(x,y,seg,tp) where x,y,seg,tp are coordinates.

o tess New argument 'marks' allows marks to be associated with tiles.

o anova.lppm Outdated argument 'override' has been removed.

o split<-.ppp Preserves the original ordering of the data, if possible.

o MultiHard, MultiStrauss, MultiStraussHard, HierStrauss Zero values in the interaction radii are now treated as NA. Improved handling of missing arguments. Printed output now respects options('width')

o linearKinhom, linearKcross.inhom, linearKdot.inhom, linearpcfinhom, linearpcfcross.inhom, linearpcfdot.inhom If the intensity argument lambda, lambdaI, lambdaJ, lambdadot is a fitted point process model, the model is first updated by re-fitting it to the data, before computing the fitted intensity.

o solutionset The expression will be evaluated using pixel arithmetic (Math.im) if it cannot be evaluated using eval.im.

o to.grey Now uses better weights for the R, G, B channels.

o rVarGamma Accelerated.

o summary.mppm, print.mppm These functions now respect options('width') and spatstat.options('terse').

o print.quadrattest Now respects options('width') and spatstat.options('terse').

o print.pp3 Now respects options('width')

o print.lpp Now respects options('width') and options('digits').

o print.owin, print.im, print.summary.owin, print.summary.im Now respect options('width').

o nnmean Now yields a vector, instead of a 1-column matrix, when there is only a single column of marks.

o pairdist.psp, crossdist.psp, nndist.psp The option 'method="Fortran"' is no longer supported. The default is 'method="C"'.

o [.hyperframe: When a row of data is extracted with drop=TRUE, the result belongs to class 'anylist'.

o installation of spatstat A Fortran compiler is no longer needed to compile spatstat from source.

o hyperframe class The internal structure of hyperframes has changed slightly: columns of objects are now stored and returned as lists of class 'anylist' or 'solist'. There should be no change in behaviour.

o datasets Internal format of the datasets bdspots, bei, clmfires, demohyper, flu, gorillas, heather, Kovesi, murchison, osteo, pyramidal, waterstriders has changed slightly to use the classes 'anylist' and 'solist'. There should be no change in behaviour.

o K3est New argument 'ratio'.

o spatstat.options New option 'par.points3d' sets default arguments for plot.pp3.

o diagnose.ppm New arguments 'xlab', 'ylab', 'rlab' determine the labels in the 4-panel plot, and new argument 'outer' controls their position. The confusing default value for 'compute.sd' has been changed.

o iplot.layered New argument 'visible' controls which layers are initially visible.

o plot.lpp New argument 'show.window' controls whether to plot the containing window.

o textstring Any number of spatial locations (x,y) can be specified, with a corresponding vector of text strings.

o plot.hyperframe New argument 'mar'

o plot.linnet New argument 'do.plot'

o summary.hyperframe Improved output.

o eval.linim Improved scoping rules.

o pixellate.owin Accelerated.

o summary.linnet Now prints more information, and respects options('digits').

o rmpoispp, rmpoint The vector of possible types of points will default to the 'names' vector of the argument 'lambda', 'n', or 'f' where appropriate.

o rpoislpp Argument 'L' can be omitted when lambda is a 'linim' or 'linfun'

o simulate.ppm, simulate.kppm, simulate.lppm, simulate.slrm New argument 'drop': if nsim = 1 and drop=TRUE, the result is a point pattern rather than a list containing one point pattern.

o runifdisc, runifpoint, rpoint, rpoispp, rmpoint, rmpoispp, rMaternI, rMaternII, rSSI, rPoissonCluster, rGaussPoisson, rstrat, rsyst, rcell, rthin, rNeymanScott, rMatClust, rThomas, rCauchy, rVarGamma, rpoispp3, runifpoint3 New argument 'drop': if nsim = 1 and drop=TRUE, the result is a point pattern rather than a list containing one point pattern.

o spatstat.options New option 'units.paren' controls the type of parenthesis enclosing the explanatory text about the unit of length, in print.ppm, plot.fv, etc.

o closepairs, crosspairs New option: what="ijd" returns only the indices i, j and the distance d

o rCauchy, rMatClust, rNeymanScott, rPoissonCluster, rThomas, rVarGamma Argument names have changed.

BUG FIXES

o sumouter A segmentation fault could occur if any data were NA. Fixed.

o simulate.kppm Simulation failed for log-Gaussian Cox processes (in simulate.kppm only) with an error message from the RandomFields package. Fixed.

o ppm, predict.ppm, profilepl Crashed sometimes with message "interaction evaluator did not return a matrix". Fixed.

o lppm step() did not work correctly on 'lppm' objects. Fixed.

o quadscheme If quadscheme() was called explicitly, with the stipulated number of tiles exceeding the number of dummy points given, then the quadrature weights were sometimes vastly inflated - total quadrature weight was much larger than window area. Spotted by Ian Renner. Fixed.

o predict.rhohat Result was incorrect for data on a non-rectangular window (and a warning was issued about incorrect vector length). Fixed.

o Math.im Unary operators did not work (e.g."-x") Fixed.

o density.ppp Crashed when at="points" if the dataset had exactly 1 point. Fixed.

o rSSI Crashed if nsim > 1. Fixed.

o influence.ppm, leverage.ppm, dfbetas.ppm Crashed or issued a warning if any quadrature points had conditional intensity zero under the model (negative infinite values of the sufficient statistic). Fixed.

o clickppp, clickpoly Did not work correctly in the RStudio display device. Fixed.

o Iest Ignored the arguments 'r' and 'eps'. Fixed.

o markvario Result was garbled, when X had more than one column of marks. Fixed.

o rMatClust, rVarGamma, rCauchy, rNeymanScott Result was a list, but not a 'solist', when nsim > 1. Fixed.

o print.mppm, summary.mppm, subfits Crashed if a Poisson interaction was implied but not given explicitly. Fixed.

o Kest Crashed if ratio=TRUE and the window was a rectangle. Fixed.

o anova.ppm Crashed sometimes with message 'models were not all fitted to the same size of dataset'. (This occurred if there were quadrature points with conditional intensity equal to zero in some models but not in all models.) Fixed.

o vcov.kppm Occasionally ran out of memory. Fixed.

o as.linim.linfun Erroneously converted the pixel values to numeric values. Fixed.

o as.owin.layered Ignored layers with zero area. Fixed.

o plot.ppm Paused the plot between frames even when there was only one frame. Fixed.

o plot.layered Did not allocate space for legends of 'lpp' objects. Fixed.

o plot.lpp Ignored symbolmap arguments like 'cex' and confused the arguments 'col' and 'cols'. Fixed.

o plot.diagppm Ignored add=TRUE in some cases. Fixed.

o iplot.layered Did not handle 'diagramobj' objects correctly. Fixed.

o plot.yardstick Changed arguments.

```
CHANGES IN spatstat VERSION 1.41-0
```

OVERVIEW

o We thank Ahmed El-Gabbas, Ute Hahn, Aruna Jammalamadaka, Ian Renner, Brian Ripley, Torben Tvedebrink and Sasha Voss for contributions.

o Fixed a bug causing a segmentation fault.

o Standard errors for kernel estimates of intensity.

o Test for segregation.

o Tessellations may now have marks.

o Nested splitting.

o More support for cluster models. Reorganised parametrisation.

o Sparse data representation of linear networks.

o More support for data on a linear network.

o New datasets: 'spiders' and 'dendrite'.

o Improvements and bug fixes.

o spatstat no longer uses Fortran.

o spatstat no longer depends on the package 'scatterplot3d'.

o spatstat now imports (rather than 'suggests') the Matrix package.

o Nickname: 'Team Australia'

NEW DATASETS

o dendrite Dendritic spines on the dendrite network of a neuron. A point pattern on a linear network. Generously contributed by Aruna Jammalamadaka.

o spiders Spider webs on the mortar lines of a brick wall. A point pattern on a linear network. Generously contributed by Sasha Voss.

NEW FUNCTIONS

o segregation.test Test of spatial segregation of types in a multitype point pattern.

o clusterfield, clusterkernel Compute the cluster kernel (offspring density) of a cluster process model, or compute the cluster field generated by superimposing copies of the cluster kernel at specified locations.

o clusterradius Compute the radius of the support of the offspring density of a cluster process model.

o as.linnet.psp Convert a line segment pattern to a linear network by guessing the connectivity using a distance threshold.

o iplot.linnet, iplot.lpp Methods for interactive plotting 'iplot' for objects of class lpp and linnet.

o Mathematical operations are now supported for pixel images on a linear network. See help(Math.linim)

o dirichlet.network, delaunay.network The linear networks formed by the Dirichlet tessellation and Delaunay triangulation.

o dirichlet.edges The edges of the Dirichlet tessellation.

o selfcut.psp Cut line segments where they cross each other.

o vertices.linnet Extract the vertices (nodes) of the linear network.

o vertexdegree Compute the degree of each vertex in a linear network.

o pixellate.linnet Pixellate a linear network.

o subset.hyperframe 'subset' method for class 'hyperframe'.

o head.hyperframe, tail.hyperframe 'head' and 'tail' methods for hyperframes.

o clickdist Measures the distance between two spatial locations clicked by the user.

o solapply, anylapply wrappers for 'lapply' which return a list of class 'solist' or 'anylist'.

o Kmark Weighted K-function. Identical to 'markcorrint' and will eventually replace it.

o marks.tess, marks<-.tess, unmark.tess: Extract or change the marks associated with the tiles of a tessellation.

o quantess Quantile tessellation: divide space into pieces which contain equal amounts of 'stuff'.

o nestsplit Nested split

o integral New generic function for integrating functions, with methods for 'im', 'msr', 'linim' and 'linfun'.

o selfcut.psp Cut line segments where they cross each other

o as.function.im Convert a pixel image to a function(x,y).

o as.linnet.linim Extract the linear network from a 'linim' object.

o pool.fv, pool.anylist New methods for 'pool'

o Window.linnet Extract the two-dimensional window containing a linear network.

SIGNIFICANT USER-VISIBLE CHANGES

o linnet, lpp A linear network can now be built in 'sparse matrix' form which requires much less memory.

o chicago The Chicago street crimes data are now stored in 'sparse matrix' form. To convert them to non-sparse form, use as.lpp(chicago, sparse=FALSE)

o kppm The parametrisation of cluster models has been reorganised. The scale parameter is now always called 'scale'. Results should be backward-compatible.

o cauchy.estK, cauchy.estpcf, matclust.estK, matclust.estpcf, thomas.estK, thomas.estpcf, vargamma.estK, vargamma.estpcf The parametrisation of cluster models has been reorganised. The scale parameter is now always called 'scale'.

o plot.kppm Also plots the cluster kernel.

o density.ppp New argument 'se' allows calculation of standard errors as well.

o plot.pp3 Now produces a genuine perspective view. New arguments control the eye position for the perspective view.

o Emark, Vmark These functions can now work with multiple columns of marks.

o pixellate.psp Can now count the number of segments that intersect each pixel, instead of the total length of intersection.

o linfun If g = linfun(f, L), the function f will always be called as f(x,y,seg,tp, ...) It is no longer expected to handle the case where 'seg' and 'tp' are absent. The resulting function g can now be called as g(X) where X is an lpp object, or as g(x,y) or g(x,y,seg,tp) where x,y,seg,tp are coordinates.

o tess New argument 'marks' allows marks to be associated with tiles.

o anova.lppm Outdated argument 'override' has been removed.

o split<-.ppp Preserves the original ordering of the data, if possible.

o MultiHard, MultiStrauss, MultiStraussHard, HierStrauss Zero values in the interaction radii are now treated as NA. Improved handling of missing arguments. Printed output now respects options('width')

o linearKinhom, linearKcross.inhom, linearKdot.inhom, linearpcfinhom, linearpcfcross.inhom, linearpcfdot.inhom If the intensity argument lambda, lambdaI, lambdaJ, lambdadot is a fitted point process model, the model is first updated by re-fitting it to the data, before computing the fitted intensity.

o solutionset The expression will be evaluated using pixel arithmetic (Math.im) if it cannot be evaluated using eval.im.

o to.grey Now uses better weights for the R, G, B channels.

o rVarGamma Accelerated.

o summary.mppm, print.mppm These functions now respect options('width') and spatstat.options('terse').

o print.quadrattest Now respects options('width') and spatstat.options('terse').

o print.pp3 Now respects options('width')

o print.lpp Now respects options('width') and options('digits').

o print.owin, print.im, print.summary.owin, print.summary.im Now respect options('width').

o nnmean Now yields a vector, instead of a 1-column matrix, when there is only a single column of marks.

o pairdist.psp, crossdist.psp, nndist.psp The option 'method="Fortran"' is no longer supported. The default is 'method="C"'.

o [.hyperframe: When a row of data is extracted with drop=TRUE, the result belongs to class 'anylist'.

o installation of spatstat A Fortran compiler is no longer needed to compile spatstat from source.

o hyperframe class The internal structure of hyperframes has changed slightly: columns of objects are now stored and returned as lists of class 'anylist' or 'solist'. There should be no change in behaviour.

o datasets Internal format of the datasets bdspots, bei, clmfires, demohyper, flu, gorillas, heather, Kovesi, murchison, osteo, pyramidal, waterstriders has changed slightly to use the classes 'anylist' and 'solist'. There should be no change in behaviour.

o K3est New argument 'ratio'.

o spatstat.options New option 'par.points3d' sets default arguments for plot.pp3.

o diagnose.ppm New arguments 'xlab', 'ylab', 'rlab' determine the labels in the 4-panel plot, and new argument 'outer' controls their position. The confusing default value for 'compute.sd' has been changed.

o iplot.layered New argument 'visible' controls which layers are initially visible.

o plot.lpp New argument 'show.window' controls whether to plot the containing window.

o textstring Any number of spatial locations (x,y) can be specified, with a corresponding vector of text strings.

o plot.hyperframe New argument 'mar'

o plot.linnet New argument 'do.plot'

o summary.hyperframe Improved output.

o eval.linim Improved scoping rules.

o pixellate.owin Accelerated.

o summary.linnet Now prints more information, and respects options('digits').

o rmpoispp, rmpoint The vector of possible types of points will default to the 'names' vector of the argument 'lambda', 'n', or 'f' where appropriate.

o rpoislpp Argument 'L' can be omitted when lambda is a 'linim' or 'linfun'

o simulate.ppm, simulate.kppm, simulate.lppm, simulate.slrm New argument 'drop': if nsim = 1 and drop=TRUE, the result is a point pattern rather than a list containing one point pattern.

o runifdisc, runifpoint, rpoint, rpoispp, rmpoint, rmpoispp, rMaternI, rMaternII, rSSI, rPoissonCluster, rGaussPoisson, rstrat, rsyst, rcell, rthin, rNeymanScott, rMatClust, rThomas, rCauchy, rVarGamma New argument 'drop'

o spatstat.options New option 'units.paren' controls the type of parenthesis enclosing the explanatory text about the unit of length, in print.ppm, plot.fv, etc.

o closepairs, crosspairs New option: what="ijd" returns only the indices i, j and the distance d

o rCauchy, rMatClust, rNeymanScott, rPoissonCluster, rThomas, rVarGamma Argument names have changed.

BUG FIXES

o sumouter A segmentation fault could occur if any data were NA. Fixed.

o simulate.kppm Simulation failed for log-Gaussian Cox processes (in simulate.kppm only) with an error message from the RandomFields package. Fixed.

o ppm, predict.ppm, profilepl Crashed sometimes with message "interaction evaluator did not return a matrix". Fixed.

o lppm step() did not work correctly on 'lppm' objects. Fixed.

o quadscheme If quadscheme() was called explicitly, with the stipulated number of tiles exceeding the number of dummy points given, then the quadrature weights were sometimes vastly inflated - total quadrature weight was much larger than window area. Spotted by Ian Renner. Fixed.

o predict.rhohat Result was incorrect for data on a non-rectangular window (and a warning was issued about incorrect vector length). Fixed.

o Math.im Unary operators did not work (e.g."-x") Fixed.

o density.ppp Crashed when at="points" if the dataset had exactly 1 point. Fixed.

o rSSI Crashed if nsim > 1. Fixed.

o influence.ppm, leverage.ppm, dfbetas.ppm Crashed or issued a warning if any quadrature points had conditional intensity zero under the model (negative infinite values of the sufficient statistic). Fixed.

o clickppp, clickpoly Did not work correctly in the RStudio display device. Fixed.

o Iest Ignored the arguments 'r' and 'eps'. Fixed.

o markvario Result was garbled, when X had more than one column of marks. Fixed.

o rMatClust, rVarGamma, rCauchy, rNeymanScott Result was a list, but not a 'solist', when nsim > 1. Fixed.

o print.mppm, summary.mppm, subfits Crashed if a Poisson interaction was implied but not given explicitly. Fixed.

o Kest Crashed if ratio=TRUE and the window was a rectangle. Fixed.

o anova.ppm Crashed sometimes with message 'models were not all fitted to the same size of dataset'. (This occurred if there were quadrature points with conditional intensity equal to zero in some models but not in all models.) Fixed.

o vcov.kppm Occasionally ran out of memory. Fixed.

o as.linim.linfun Erroneously converted the pixel values to numeric values. Fixed.

o as.owin.layered Ignored layers with zero area. Fixed.

o plot.ppm Paused the plot between frames even when there was only one frame. Fixed.

o plot.layered Did not allocate space for legends of 'lpp' objects. Fixed.

o plot.lpp Ignored symbolmap arguments like 'cex' and confused the arguments 'col' and 'cols'. Fixed.

o plot.diagppm Ignored add=TRUE in some cases. Fixed.

o iplot.layered Did not handle 'diagramobj' objects correctly. Fixed.

o plot.yardstick Changed arguments.

```
CHANGES IN spatstat VERSION 1.40-0
```

OVERVIEW

o We thank Markus Herrmann, Peter Kovesi, Andrew Lister, Enrique Miranda, Tuomas Rajala, Brian Ripley, Dominic Schuhmacher and Maxime Woringer for contributions.

o Important bug fixes.

o Mathematical operators now apply to images.

o Parametric estimates of relative risk from fitted point process models.

o Standard errors for relative risk (parametric and non-parametric).

o Kernel smoothing and rose diagrams for angular data.

o Perceptually uniform colour maps.

o Hierarchical interactions for multitype patterns.

o Hard core parameters in all interactions no longer need to be specified and will be estimated from data.

o Improvements to analysis of deviance and model selection.

o New datasets.

o New vignette, summarising all datasets installed with spatstat.

o Tests and diagnostics now include a Monte Carlo option.

o Faster checking of large datasets.

o Faster simulations.

o Code for drawing diagrams (arrows, scale bars).

o Version nickname: 'Do The Maths'

NEW DATASETS

o bdspots Breakdown spots on microelectronic capacitor electrodes. Generously contributed by Prof Enrique Miranda.

o Kovesi Colour maps with perceptually uniform contrast. Generously contributed by Peter Kovesi.

NEW FUNCTIONS

o Mathematical operations are now supported for images. For example: alpha <- atan(bei.extra$grad) * 180/pi See help(Math.im)

o relrisk.ppm Spatially-varying probabilities of different types of points predicted by a fitted point process model.

o circdensity Kernel density estimate for angular data

o rose Rose diagram (rose of directions) for angular data

o nnorient Nearest neighbour orientation distribution.

o AIC.ppm Calculate AIC of a Gibbs model using Takeuchi's rule.

o interp.colours Interpolate a sequence of colour values.

o anyDuplicated.ppp, anyDuplicated.ppx Fast replacements for any(duplicated(x)) for point patterns.

o textstring, onearrow, yardstick Objects representing a text string, an arrow, or a scale bar, for use in drawing spatial diagrams.

o plot.imlist, image.imlist, contour.imlist Methods for the new class 'imlist'

o [<-.layered, [[<-.layered More support for class 'layered'

SIGNIFICANT USER-VISIBLE CHANGES

o (vignettes) New vignette 'datasets' summarises all the datasets installed with the spatstat package.

o relrisk The function relrisk is now generic, with methods for ppp and ppm. New argument 'relative' specifies whether to calculate the relative risk or the absolute probability of each type of point. New argument 'se' specifies whether to calculate standard errors.

o plot.im The default colour map for plotting images, specified by spatstat.options('image.colfun'), has been changed to a perceptually uniform map.

o DiggleGratton, Fiksel, MultiHard, MultiStraussHard The hard core distance parameters in these models can now be omitted by the user, and will be estimated automatically from data (by the 'self-starting' feature of interactions). This was already true of Hardcore and StraussHard.

o Hybrid Hybrid models now apply the 'self-starting' feature to each component model.

o anova.ppm Can now reconcile models fitted using different dummy points, different values of 'rbord', different values of 'use.gam', etc.

o profilepl New argument 'aic' makes it possible to optimise the parameters by minimising AIC.

o profilepl No longer requires values for parameters which are 'optional' (such as the hard core distance).

o rmh, simulate.ppm, rmh.ppm, rmh.default The Metropolis-Hastings algorithm now starts by deleting any points in the initial state that are 'illegal' (i.e. whose conditional intensity is equal to zero). This ensures that the result of rmh never contains illegal points.

o runifpoint, rpoispp, rStrauss, rHardcore, rStraussHard, rDiggleGratton, rDGS, runifdisc, rpoint, rMaternI, rMaternII, rSSI, rPoissonCluster, rGaussPoisson, rstrat, rsyst, rcell, rthin, rjitter, rNeymanScott, rMatClust, rThomas, rCauchy, rVarGamma, rmpoint, rmpoispp, runifpointOnLines, rpoisppOnLines, runiflpp, rpoislpp, runifpointx, rpoisppx, runifpoint3, rpoispp3 These random point pattern generators now have an argument 'nsim' specifying the number of simulated realisations to be generated.

o pairorient New argument 'cumulative'. New algorithm to compute kernel estimate of probability density. Default behaviour changed. Argument 'units' has been renamed 'unit' for consistency. Labels and descriptions of columns have been corrected.

o predict.ppm New syntax (backward-compatible). New argument 'se' replaces option 'type="se"'. Old argument 'total' is deprecated: use 'window' and set 'type="count"'.

o cdf.test The methods for class 'ppm' and 'lppm' now handle Gibbs models and perform a Monte Carlo test in this case.

o lurking, diagnose.ppm Lurking variable plot can now include simulation envelopes.

o rmh.ppm New argument 'w' determines the window in which the simulated pattern is generated.

o ppp Accelerated.

o Gcom, Gres When conditional=TRUE and restrict=TRUE, the Hanisch estimate was not calculated exactly as described in Appendix E.1 of Baddeley, Rubak and Moller (2011). The intensity was estimated on the full window rather than the eroded window. Fixed.

o step, drop1, add1, extractAIC The AIC of a Gibbs model is now calculated using Takeuchi's rule for the degrees of freedom.

o model.matrix.ppm, model.matrix.kppm New argument 'Q' allows prediction at any desired locations.

o vcov.ppm New argument 'fine' gives more control over computation.

o predict.ppm For multitype models, when the result is a list of images, the names of list entries are now identical to the mark levels (e.g. "hickory" instead of "markhickory")

o print.slrm Output now respects options('width')

o image.listof New argument 'ribmar' controls margin space around the ribbon when equal.ribbon=TRUE.

o integral.im New argument 'domain' specifies the domain of integration.

o plot.fasp New argument 'transpose' allows rows and columns to be exchanged.

o plot.im The list 'ribargs' can now include the parameter 'labels'.

o rmh, rpoint, rpoispp, rmpoint, rmpoispp Accelerated, for inhomogeneous processes.

o stienen Now recognises the parameter 'lwd'.

o suffstat Accelerated (also affects ppm with method='ho').

o Poisson, AreaInter, BadGey, Concom, DiggleGatesStibbard, DiggleGratton, Fiksel, Geyer, Hardcore, Hybrid, LennardJones, MultiHard, MultiStrauss, MultiStraussHard, OrdThresh, Ord, PairPiece, Pairwise, SatPiece, Saturated, Softcore, Strauss, StraussHard, Triplets These functions can now be printed (by typing the function name) to give a sensible description of the required syntax.

o fitin A plot of the fitted interpoint interaction of a point process model e.g. plot(fitin(ppm(swedishpines ~ 1, Strauss(9)))) now shows the unit of length on the x-axis.

o fitin Plots of the fitted interpoint interaction are now possible for some higher-order interactions such as Geyer and AreaInter.

o anova.ppm New argument 'warn' to suppress warnings.

o rmhmodel.ppm Argument 'win' renamed 'w' for consistency with other functions.

o print.ppm Printed output for the fitted regular parameters now respects options('digits').

o print.ppm, print.summary.ppm Output now respects options('width') and spatstat.options('terse')

o print.ppm By default, standard errors are not printed for a model fitted with method="logi" (due to computational load)

o plot.profilepl Now recognises 'lty', 'lwd', 'col' etc

o vesicles, gorillas Some of the raw data files for these datasets are also installed in spatstat for demonstration and training purposes.

BUG FIXES

o rmh, rmh.ppm, rmh.default, simulate.ppm The result of simulating a model with a hard core did not necessarily respect the hard core constraint, and simulation of a model with strong inhibition did not necessarily converge. This only happened if the first order trend was large, the starting state (n.start or x.start) was not given, and the number of iterations (nrep) was not very large. It occurred because of a poor choice for the default starting state. Bug was present since about 2010. Fixed.

o markcorrint Results were completely incorrect. Bug introduced in spatstat 1.39-0, october 2014. Fixed.

o Kinhom Ignored argument 'reciplambda2' in some cases. Bug introduced in spatstat 1.39-0, october 2014. Fixed.

o relrisk When at="pixels", a small fraction of pixel values were sometimes wildly inaccurate, due to numerical errors. This affected the range of values in the result, and therefore the appearance of plots. Fixed.

o model.images Crashed if the model was multitype. Fixed.

o profilepl Crashed in some cases when the interaction was multitype. [Spotted by Andrew Lister.] Fixed.

o profilepl Crashed if the model involved covariates that were not given in a 'data' argument. Fixed.

o envelope.ppm Crashed if global=TRUE and savefuns=TRUE. Fixed.

o setminus.owin Crashed if the result was empty and the input was polygonal. Fixed.

o predict.ppm Crashed sometimes when type="cif" and ngrid was very large. Fixed.

o pixelquad If X was a multitype point pattern, the result was mangled. Fixed.

o relrisk Did not accept a character string value for the argument 'case'. Fixed.

o intensity.ppm Format of result was incorrect for ppm(Y ~ 1) where Y is multitype. Fixed.

o $<-.hyperframe Columns containing character values were converted to factors. Fixed.

o clickppp Sometimes filled the window in solid black colour.. Fixed.

o plot.psp Ignored 'show.all' in some cases. Fixed.

o plot.ppp Warned about NA values amongst the marks, even if there were no NA's in the column(s) of marks selected by the argument 'which.marks'. Fixed.

o stienen Did not suppress the border circles when border=FALSE. Fixed.

```
CHANGES IN spatstat VERSION 1.39-1
```

OVERVIEW

o Urgent bug fix.

o We thank Suman Rakshit and Brian Ripley for contributions.

BUG FIXES

o bdry.mask, convexhull In R-devel only, these functions could return an empty window, causing errors in other packages. [Spotted by Brian Ripley.] Fixed.

o project2segment An error occurred if any line segments had length zero. [Spotted by Suman Rakshit.] Fixed.

```
CHANGES IN spatstat VERSION 1.39-0
```

OVERVIEW

o We thank Shane Frank, Shaaban Ghalandarayeshi, Ute Hahn, Mahdieh Khanmohammadi, Nicoletta Nava, Jens Randel Nyengaard, Sebastian Schutte, Rasmus Waagepetersen and Carl G. Witthoft for contributions.

o ANOVA extended to Gibbs models.

o Improved algorithm for locally-scaled K-function.

o Leave-one-out calculation of fitted values in ppm objects.

o New dataset: presynaptic vesicles.

o Geometrical operations with windows and images.

o More edge corrections for K-function.

o Improved handling and plotting of 'fv' objects.

o Utilities for perspective views of surfaces.

o New classes 'anylist', 'solist' will ultimately replace 'listof'.

o Bug fixes.

o Version nickname: 'Smoke and Mirrors'

NEW DATASETS

o vesicles Synaptic vesicles (includes raw data files for training purposes)

NEW CLASSES

o anylist List of objects. (A replacement for 'listof')

o solist List of two-dimensional spatial objects. (A replacement for some uses of 'listof')

NEW FUNCTIONS

o perspPoints, perspLines, perspSegments, perspContour Draw points and lines on a surface, as seen in perspective view.

o hopskel.test Hopkins-Skellam test of CSR

o project2set For each data point in a point pattern X, find the nearest spatial location in a given window W.

o stienen, stienenset Stienen diagrams

o dirichlet.vertices Vertices of the Dirichlet tessellation

o discs Union of discs. Given a point pattern dataset recording the locations and diameters of objects, find the region covered by the objects.

o increment.fv Increments of a summary function: g(x) = f(x+h)-f(x-h).

o rotmean Rotational average of pixel values in an image

o fardist Distance from each pixel/data point to farthest part of window boundary

o circumradius.owin Circumradius of a window

o rmax.Trans, rmax.Ripley
Compute the maximum distance 'r' for which the
translation edge correction and isotropic edge correction

are valid.

o is.grey Determines whether a colour value is a shade of grey.

o harmonise Convert several objects of the same class to a common format. (New generic function with existing methods harmonise.im and harmonise.fv)

o area New generic function, with methods for 'owin' and 'default'.

o Fhazard Hazard rate of empty space function

o anylist, as.anylist, [.anylist, [<-.anylist, print.anylist, summary.anylist Support for new class 'anylist'

o solist, as.solist, [.solist, [<-.solist, print.solist, summary.solist Support for new class 'solist'

o plot.anylist, plot.solist Plot methods for the classes 'anylist' and 'solist' (Currently identical to 'plot.listof')

SIGNIFICANT USER-VISIBLE CHANGES

o anova.ppm Now applies to Gibbs models as well as Poisson models, using adjusted composite likelihood ratio test statistic.

o persp.im If visible=TRUE, the algorithm will also calculate which pixels of x are visible in the perspective view. This is useful for drawing points or lines on a perspective surface.

o Kscaled Improved algorithm [thanks to Ute Hahn.] New arguments 'renormalise' and 'normpower' allow renormalisation of intensity, similar to Kinhom.

o Kest New option: correction="rigid" computes the rigid motion correction.

o pairwise interactions Fitted parameters and other calculations for pairwise interaction models DiggleGatesStibbard, DiggleGratton, Fiksel, Geyer, Strauss may change slightly due to a change in handling numerical rounding effects.

o eval.fv Functions no longer need to have exactly the same sequence of 'r' values. They will now be made compatible using 'harmonise.fv'.

o fitted.ppm New argument 'leaveoneout' allows leave-one-out calculation of fitted intensity at original data points.

o Kinhom, Linhom New argument 'leaveoneout' specifies whether the leave-one-out rule should be applied when calculating the fitted intensities.

o crosspaircounts Results may change slightly due to a change in handling numerical rounding effects.

o Fest, Gest New argument 'domain' supports bootstrap methods.

o plot.fv New argument 'mathfont' determines the font (e.g. plain, italic, bold) for mathematical expressions on the axes and in the legend. Defaults to italic.

o scanpp Upgraded to handle multiple columns of mark data.

o circumradius The function 'circumradius' is now generic, with methods for the classes 'owin' and 'linnet'.

o edge.Trans New argument 'give.rmax'

o fvnames, plot.fv The symbol '.a' is now recognised. It stands for 'all function values'.

o as.function.fv Argument 'extrapolate' can have length 1 or 2.

o varblock New argument 'confidence' determines the confidence level.

o $<-.fv This can now be used to add an extra column to an 'fv' object (previously it refused).

o minnndist, maxnndist New argument 'positive'. If TRUE, coincident points are ignored: the nearest-neighbour distance of a point is the distance to the nearest point that does not coincide with the current point.

o plot.fv Improved handling of 'shade' argument.

o Kmeasure Now passes '...' arguments to as.mask()

o Ksector
Now allows start < 0.

New arguments 'units' and 'domain'.

o pairorient New arguments 'units' and 'domain'.

o eroded.areas New argument 'subset'

o disc New argument 'delta'

o plot.plotppm New argument 'pppargs'

o harmonise.fv, harmonise.im These are now methods for the new generic 'harmonise'

o Fest, Gest These functions now also compute the theoretical value of hazard for a Poisson process, if correction = "km".

o with.fv Improved mathematical labels.

o Gfox, Jfox Improved mathematical labels.

o area.owin This function is now a method for the new generic 'area'

o edges Default for argument 'check' changed to FALSE.

BUG FIXES

o varblock Calculations were incorrect if more than one column of edge corrections was computed. [Bug introduced in spatstat 1.21-1, november 2010.] Fixed.

o varblock Crashed if one of the quadrats contained no data points. Fixed.

o lohboot Interval was calculated wrongly when global=TRUE and fun="Lest" or "Linhom". Fixed.

o nnmark Crashed when at="points" if there was only a single column of marks. [Spotted by Shane Frank.] Fixed.

o plot.msr Some elements of the plot were omitted or cut off. Fixed.

o plot.msr Did not work with 'equal.scales=TRUE'. Fixed.

o plot.msr, augment.msr Crashed if every data point was duplicated. Fixed.

o as.im.owin Crashed if X was a 1 x 1 pixel array. Fixed.

o owin Coordinates of polygon data were altered slightly when fix=TRUE. [Spotted by Carl Witthoft.] Fixed.

o objects of class 'fv' Assigning a new value to names(x) or colnames(x) or dimnames(x) would cause the internal data format to become corrupted. Fixed.

o to.grey, complementarycolour Did not work properly on 'colourmap' objects. Fixed.

o Kest Ignored argument 'var.approx' if the window was a rectangle. Fixed.

o rmh.ppm, rmhmodel.ppm Ignored the argument 'new.coef'. [Spotted by Sebastian Schutte] Fixed.

o as.function.fv The meanings of 'extrapolate=TRUE' and 'extrapolate=FALSE' were swapped. Fixed.

o varblock Handled the case 'fun=Lest' incorrectly. Fixed.

o [.fv Sometimes garbled the internal data format, causing plot.fv to crash. Fixed.

o range.fv Sometimes returned NA even when na.rm=TRUE. Fixed.

o Fest Argument 'eps' was not interpreted correctly. Fixed.

o plot.fv Argument 'lwd' was not passed to legend()

o flipxy.owin Sometimes deleted the name of the unit of length. Fixed.

```
CHANGES IN spatstat VERSION 1.38-1
```

OVERVIEW

o We thank Ute Hahn and Xavier Raynaud for contributions.

o Urgent Bug Fixes.

o Nickname: 'Le Hardi'

NEW FUNCTIONS

o "[<-.fv", "$<-.fv" Subset replacement methods for 'fv' objects.

SIGNIFICANT USER-VISIBLE CHANGES

o clarkevans.test Simulations are now performed with a fixed number of points.

o plot.owin, plot.ppp, plot.psp, plot.im The default size of the outer margin of white space has been reduced.

o dclf.test Improved information in printed output.

BUG FIXES

o update.ppm Results were incorrect in several cases. [Spotted by Xavier Raynaud.] Bug introduced in spatstat 1.38-0. Fixed.

o Kinhom, Linhom Calculations were incorrect if 'lambda' was a fitted point process model. [Spotted by Xavier Raynaud.] Bug introduced in spatstat 1.38-0. Fixed.

o envelope.envelope Ignored the arguments 'global' and 'VARIANCE'. Fixed.

o fv objects If 'f' was an object of class 'fv', then an assignment like f$name <- NULL mangled the internal format of the object 'f', leading to errors in print.fv and plot.fv. [Spotted by Ute Hahn.] Fixed.

o split.ppp split(X, A) where A is a rectangular tessellation, produced errors if the window of 'A' did not include the window of 'X'. [Spotted by Ute Hahn.] Fixed.

o names<-.hyperframe Mangled the internal format. [Spotted by Ute Hahn.] Fixed.

o plot.fv y axis label was incorrect in some cases when the 'fv' object had only a single column of function values. [Spotted by Ute Hahn.] Fixed.

```
CHANGES IN spatstat VERSION 1.38-0
```

OVERVIEW

o We thank Malissa Baddeley, Colin Beale, Oscar Garcia, Daniel Esser, David Ford, Eric Gilleland, Andrew Hardegen, Philipp Hunziker, Abdollah Jalilian, Tom Lawrence, Lore De Middeleer, Robin Milne, Mike Porter, Suman Rakshit, Pablo Ramon, Jason Rudokas, Christopher Ryan, Dominic Schuhmacher, Medha Uppala and Rasmus Waagepetersen for contributions.

o spatstat now Requires the package 'goftest' and Suggests the package 'Matrix'.

o New dataset: 'sporophores'

o Palm likelihood method for fitting cluster processes and Cox processes.

o Quasi-likelihood and weighted composite likelihood methods for estimating trend in cluster processes and Cox processes.

o Further extensions to model formulas in ppm and kppm.

o Faster variance calculations for ppm objects.

o One-sided tests and one-sided envelopes of summary functions.

o Cramer-Von Mises and Anderson-Darling tests of spatial distribution.

o Cressie-Read test statistic in quadrat counting tests.

o Spatial cumulative distribution functions.

o Faster algorithm for point pattern matching.

o Improvements to plots.

o Increased support for envelopes.

o New generic functions 'Window', 'Frame' and 'domain'.

o Directional K-function and directional distribution.

o Raster calculations accelerated.

o Summary functions accelerated.

o Many improvements and bug fixes.

o Version nickname: 'Wicked Plot'

NEW DATASETS

o sporophores Spatial pattern of three species of mycorrhizal fungi around a tree. [Contributed by E. David Ford.]

NEW FUNCTIONS

o improve.kppm Re-estimate the trend in a kppm (cluster or Cox) model using quasi-likelihood or weighted first-order composite likelihood. [Contributed by Abdollah Jalilian and Rasmus Waagepetersen.]

o Window, Window<- Generic functions to extract and change the window of a spatial object in two dimensions. Methods for ppp, psp, im, and many others.

o Frame, Frame<- Generic functions to extract and change the containing rectangle ('frame') of a spatial object in two dimensions.

o domain Generic function to extract the spatial domain of a spatial object in any number of dimensions.

o Ksector Directional version of the K-function.

o pairorient Point pair orientation distribution.

o spatialcdf Compute the spatial cumulative distribution of a spatial covariate, optionally using spatially-varying weights.

o cdf.test [Supersedes 'kstest'.] Test of goodness-of-fit of a Poisson point process model. The observed and predicted distributions of the values of a spatial covariate are compared using either the Kolmogorov-Smirnov, Cramer-Von Mises or Anderson-Darling test.

o berman.test Replaces 'bermantest'.

o harmonise.fv Make several functions compatible.

o simulate.lppm Simulate a fitted point process model on a linear network.

o subset.ppp, subset.lpp, subset.pp3, subset.ppx Methods for 'subset', for point patterns.

o closepairs.pp3, crosspairs.pp3 Low-level functions to find all close pairs of points in three dimensions

o volume.linnet Method for the generic 'volume'. Returns the length of the linear network.

o padimage Pad the border of a pixel image.

o as.layered Convert spatial data to a layered object.

o panel.contour, panel.image, panel.histogram Panel functions for 'pairs' plots.

o range.fv, min.fv, max.fv Range, minimum and maximum of function values.

SIGNIFICANT USER-VISIBLE CHANGES

o ppm.formula The left hand side of the formula can now be the name of an object in the list 'data', or an expression involving such objects.

o ppm The right hand side of the formula can now include the symbol '.' representing all covariates in the list 'data'.

o ppm New argument 'subset' makes it possible to fit the model in a subset of the spatial domain defined by an expression.

o kppm New option: method="palm", will fit the model by maximising Palm likelihood.

o pppdist Substantially accelerated. New argument 'auction' controls choice of algorithm.

o rhohat New arguments 'weights' and 'horvitz' for weighted calculations.

o persp.im Surface heights and colours can now be controlled by different images. Option to draw a grey apron around the sides of the perspective plot. Return value has a new attribute 'expand'.

o plot.listof New arguments 'halign' and 'valign' give improved control over the alignment of panels.

o plot.listof If all components of the list are objects of class 'fv' representing functions, then if equal.scales=TRUE, these functions will all be plotted with the same axes (i.e. the same xlim and the same ylim).

o envelope The argument 'transform' is now processed by 'with.fv' giving more options, such as 'transform=expression(. - r)'

o envelope, dclf.test, mad.test One-sided tests and one-sided envelopes can now be produced, by specifying the argument 'alternative'.

o dclf.test, mad.test A pointwise test at fixed distance 'r' can now be performed by setting rinterval = c(r,r).

o envelope New arguments 'fix.n' and 'fix.marks' for envelope.ppp and envelope.ppm make it easy to generate simulated patterns conditional on the total number of points, or on the number of points of each type.

o quadrat.test Can now calculate the Cressie-Read test statistic instead of the Pearson X2 statistic.

o Kres, Gres, Kcom, Gcom, psst, psstA, psstG New argument 'model' makes it easier to generate simulation envelopes of the residual summary functions.

o layered, plot.layered The layer plot arguments can include the argument '.plot' specifying a function to perform the plotting instead of the generic 'plot'.

o deriv.fv New arguments make it possible to differentiate a periodic function.

o ppm Argument 'data' or 'covariates' can now include entries which are not spatial covariates, provided they do not appear in the model formula.

o closepairs, crosspairs These functions are now generic, with methods for 'ppp' and 'pp3'

o rLGCP Updated to conform to new usage of RandomFields package. Argument syntax has changed. Now allows control over pixel resolution.

o bw.diggle New arguments 'correction' and 'hmax' for controlling the calculation.

o predict.lppm New argument 'new.coef' for computing predictions with a different vector of model coefficients.

o predict.ppm If 'locations' is a pixel image, its pixels determine the spatial locations for prediction.

o cut.ppp Argument 'z' can now be a window.

o split.ppp Argument 'f' can now be a window.

o print.ppm, summary.ppm, coef.summary.ppm The table of parameter estimates, standard errors and confidence intervals now also includes the value of the (signed square root) Wald test statistic.

o plot.im Now automatically detects problems in some Windows graphics displays and tries to avoid them.

o plot.im The position of axis tick marks alongside the colour ribbon can now be controlled using the parameter 'at' in the argument 'ribargs'.

o plot.ppp Can now plot numeric marks using characters chosen by 'pch' or 'chars' with size determined by mark value.

o plot.ppp New argument 'meansize' for controlling mark scale.

o hsvim, rgbim New argument 'autoscale' causes automatic scaling of colour channel values.

o plot.ppp If type='n', a legend is now displayed when x is a marked point pattern.

o whist Accelerated by a factor of 5.

o Fest, Jest Accelerated by a factor of 2 to 3.

o fryplot Accelerated. Now displays a legend if the point pattern is marked. Now handles numerical marks nicely. New argument 'axes'.

o frypoints Accelerated. New arguments 'to', 'from' and 'dmax'.

o duplicated.ppp New option: rule = 'unmark'

o rjitter Argument 'radius' now has a default.

o Smooth.msr New argument 'drop'

o LambertW Now handles NA and infinite values.

o update.ppm Now handles formulae with a left-hand side.

o raster.x, raster.y, raster.xy These functions can now handle images, as well as masks.

o Smooth.ppp If the mark values are exactly constant, the resulting smoothed values are now exactly constant.

o eval.im, eval.fv, eval.fasp Argument 'envir' can now be a list, instead of an environment.

o plot.ppp The printout (of the resulting symbol map object) now displays the numerical value of the mark scale.

o with.fv Improved mathematical labels.

o plot.fv Improved mathematical labels on x axis.

o ppm Improved error messages.

o vcov.ppm Computations greatly accelerated for Hybrid interactions and for Area-interaction models.

o vcov.kppm Computations greatly accelerated (when fast=TRUE)

o interp.im Argument 'x' can now be a point pattern.

o pool.envelope Improved handling of text information.

o miplot Improved layout.

o print.summary.ppp Improved layout. Now respects spatstat.options('terse')

o print.profilepl Improved layout. Now respects spatstat.options('terse')

o anova.ppm Now respects spatstat.options('terse')

o print.fv, print.envelope Now respect spatstat.options('terse') and options('width')

o summary.envelope Now respects options('width')

o kstest, bermantest These functions will soon be Deprecated. They are retained only for backward compatibility.

BUG FIXES

o vcov.ppm Sometimes gave wrong answers for Poisson models fitted by method='logi'. Fixed.

o unnormdensity If weights were missing, the density was normalised, contrary to the documentation. Fixed.

o logLik.ppm, anova.ppm, AIC For models fitted by 'ippm', the number of degrees of freedom was incorrect. Fixed.

o im.apply Pixels outside the window were not assigned the value NA as they should. Fixed.

o pixellate.owin Crashed, unpredictably, if the pixel raster had unequal numbers of rows and columns. [Spotted by Rasmus Waagepetersen.] Fixed.

o vcov.ppm Crashed for pairwise interaction models fitted by method="logi". Fixed.

o predict.ppm Crashed for models fitted by method="logi" if the model included external covariates. Fixed.

o predict.ppm Crashed if the argument 'covariates' or 'data' in the original call to 'ppm' included entries that were not spatial covariates. [These entries were ignored by ppm but caused predict.ppm to crash.] Fixed.

o simulate.kppm, rNeymanScott, rThomas, rMatClust Crashed randomly when simulating an inhomogeneous model. [Spotted by Philipp Hunziker.] Fixed.

o bw.diggle In some extreme cases, generated an error message about `NaN values in Foreign function call.' [Spotted by Colin Beale.] Fixed.

o textureplot Crashed if 'spacing' was too large. Fixed.

o superimpose.psp Crashed if the result was empty. Fixed.

o istat Crashed with an error message about 'vars'. Fixed.

o dirichlet, delaunay, delaunay.distance Crashed in rare cases due to a problem in package 'deldir'. [Spotted by Pierre Legendre.] Fixed.

o rgbim, hsvim Crashed if any argument was constant. Fixed.

o scaletointerval Crashed if x was constant. Fixed.

o linnet, [.linnet Crashed if the result contained only a single vertex. [Spotted by Daniel Esser.] Fixed.

o plot.fv If some of the function values were NA, they were replaced by fictitious values (by linearly interpolating). Fixed.

o crossdist.ppp Ignored argument 'squared' if periodic=FALSE. [Spotted by Mike Porter.] Fixed.

o marks<-.ppp Ignored argument 'drop'. [Spotted by Oscar Garcia.] Fixed.

o update.ppm Sometimes did not respect the argument 'use.internal'. Fixed.

o plot.rhohat Did not respect the argument 'limitsonly'. Fixed.

o contour.im Argument 'axes' defaulted to TRUE, but FALSE was intended. Fixed.

o print.hyperframe, as.data.frame.hyperframe Column names were mangled if the hyperframe had a single row. Fixed.

o as.psp.data.frame Generated a warning about partially-matched names in a data frame. [Spotted by Eric Gilleland.] Fixed.

o plot.leverage.ppm Generated a warning from 'contour.default' if the leverage function was constant. Fixed.

o plot.diagppm Issued warnings about unrecognised graphics parameters. Fixed.

o update.symbolmap Discarded information about the range of input values. Fixed.

o plot.fv Label for y axis was garbled, if argument 'shade' was given. Fixed.

o plot.ppp The legend was sometimes plotted when it should not have been (e.g. when add=TRUE). Fixed.

o plot.listof, plot.im In an array of plots, containing both images and other spatial objects, the titles of the panels were not correctly aligned. Fixed.

o plot.tess, plot.quadratcount Ignored arguments like 'cex.main'. Fixed.

o iplot Navigation buttons (Left, Right, Up, Down, Zoom In, Zoom Out) did not immediately refresh the plot. Fixed.

o iplot.layered Reported an error 'invalid argument type' if all layers were deselected. Fixed.

```
CHANGES IN spatstat VERSION 1.37-0
```

OVERVIEW

o Ege Rubak is now a joint author of spatstat.

o We thank Peter Forbes, Tom Lawrence and Mikko Vihtakari for contributions.

o Spatstat now exceeds 100,000 lines of code.

o New syntax for point process models (ppm, kppm, lppm) equivalent to syntax of lm, glm, ...

o Covariates in ppm and kppm can now be tessellations.

o Confidence intervals and prediction intervals for fitted models.

o Quasirandom point patterns and sequences.

o Plots using texture fill.

o Support for mappings from data to graphical symbols and textures.

o Automatic re-fitting of model in Ginhom, Kinhom, Finhom, Jinhom.

o Support for Mixed Poisson distribution.

o Interpretation of mark scale parameters has changed in plot.ppp

o Syntax of multitype interactions (eg MultiStrauss) has changed.

o Bug fix in Metropolis-Hastings simulation of 'StraussHard' models

o Changed default behaviour of perfect simulation algorithms.

o Improvements to layout of text output.

o Version nickname: 'Model Prisoner'

NEW CLASSES

o symbolmap An object of class 'symbolmap' represents a mapping from data to graphical symbols

o texturemap An object of class 'texturemap' represents a mapping from data to graphical textures.

NEW FUNCTIONS

o split.hyperframe, split<-.hyperframe methods for split and split<- for hyperframes.

o dmixpois, pmixpois, qmixpois, rmixpois (log-)normal mixture of Poisson distributions.

o vdCorput, Halton, Hammersley, rQuasi quasirandom sequences and quasirandom point patterns.

o Smoothfun create a function(x,y) equivalent to the result of Smooth.ppp

o minnndist, maxnndist Faster ways to compute min(nndist(X)), max(nndist(X))

o add.texture Draw a simple texture inside a specified region.

o textureplot Display a factor-valued pixel image using texture fill.

o texturemap Create a texture map

o plot.texturemap Plot a texture map in the style of a legend

o symbolmap Create a symbol map

o update.symbolmap Modify a symbol map

o invoke.symbolmap Apply symbol map to data values, and plot them

o plot.symbolmap Plot the symbol map in the style of a legend

o as.owin.boxx Converts a 'boxx' to an 'owin' if possible.

o ellipse Create an elliptical window.

o clickbox Interactively specify a rectangle, by point-and-click on a graphics device.

o complementarycolour Compute the complementary colour value of a given colour value, or the complementary colour map of a given colour map.

o gauss.hermite Gauss-Hermite quadrature approximation to the expectation of any function of a normally-distributed random variable.

o boundingbox Generic function, replaces bounding.box

o edges Extract boundary edges of a window. Replaces and extends 'as.psp.owin'

o pixelcentres Extract centres of pixels as a point pattern.

SIGNIFICANT USER-VISIBLE CHANGES

o ppm, kppm, lppm NEW SYNTAX FOR POINT PROCESS MODELS The model-fitting functions 'ppm', 'kppm' and 'lppm' now accept a syntax similar to 'lm' or 'glm', for example ppm(X ~ Z), but still accept the older syntax ppm(X, ~Z). To support both kinds of syntax, the functions 'ppm' and 'kppm' are now generic, with methods for the classes 'formula', 'ppp' and 'quad'. The 'formula' method handles a syntax like ppm(X ~ Z) while the 'ppp' method handles the old syntax ppm(X, ~Z). Similarly 'lppm' is generic with methods for 'formula' and 'lpp'.

o ppm, kppm, lppm Covariates appearing in the model formula can be objects which exist in the R session, instead of always having to be elements of the list `covariates'.

o ppm.formula, kppm.formula, lppm.formula Formulae involving polynom() are now expanded, symbolically, so that polynom(x, 3) becomes x + I(x^2) + I(x^3) and polynom(x,y,2) becomes x + y + I(x^2) + I(x*y) + I(y^2). This neatens the model output, and also makes it possible for anova() and step() to add or delete single terms in the polynomial.

o predict.ppm New argument 'interval' allows confidence intervals or prediction intervals to be calculated.

o predict.ppm New argument 'total' allows for prediction of the total number of points in a specified region.

o plot.ppp, plot.lpp For marked point patterns, a legend is automatically added to the plot, by default. Arguments have changed: new arguments include parameters of the legend, and an optional symbol map. Result has changed: it is now an object of class 'symbolmap'.

o plot.ppp, plot.lpp Interpretation of the parameters 'markscale' and 'maxsize' has changed. The size of a circle in the plot is now defined as the circle's diameter instead of its radius. (Size of a square is measured, as before, by its side length).

o parres Now handles the case where the fitted model is not separable but its restriction to the given 'subregion' is separable.

o envelope Now issues a warning if the usage of envelope() appears to be `invalid' in the sense that the simulated patterns and the data pattern have not been treated equally.

o Kinhom, Finhom, Ginhom, Jinhom New argument 'update'. If 'lambda' is a fitted model (class ppm or kppm) and update=TRUE, the model is re-fitted to the data pattern, before the intensities are computed.

o rDiggleGratton, rDGS, rHardcore, rStrauss, rStraussHard By default the point pattern is now generated on a larger window, and trimmed to the original window. New argument expand=TRUE.

o MultiStrauss, MultiHard, MultiStraussHard The syntax of these functions has changed. The new code should still accept the old syntax.

o rhohat rhohat.ppp and rhohat.quad have new argument 'baseline'

o ippm Algorithm improved. Argument syntax changed.

o default.dummy, quadscheme Dummy points can now be generated by a quasirandom sequence.

o plot.owin The window can now be filled with one of 8 different textures. Arguments changed.

o ppm, kppm Covariates in the model can now be tessellations.

o [.im New argument 'tight' allows the resulting image to be trimmed to the smallest possible rectangle.

o [.psp, rlinegrid, rpoisline These functions now handle binary mask windows.

o rotate The user can specify the centre of rotation.

o rescale rescale() and all its methods now have argument 'unitname' which can be used to change the name of the unit of length.

o anova.ppm Output format has been improved. Number of columns of result has changed.

o print.ppp, print.summary.ppp, print.owin, print.summary.owin, print.im, print.summary.im, print.fv, print.msr, print.profilepl These functions now avoid over-running the text margin (i.e. they respect options('width') where possible).

o layerplotargs<- Now handles any spatial object, converting it to a 'layered' object.

o effectfun Improved display in case se.fit=TRUE.

o scaletointerval New argument 'xrange'

o contour.im New argument 'show.all'. Default value of 'axes' changed to FALSE.

o identify.ppp Now handles multivariate marks.

o plot.listof Improved layout. New arguments 'hsep', 'vsep'. Argument 'mar.panel' may have length 1, 2 or 4.

o plot.splitppp This function is no longer identical to plot.listof. Instead it is a much simpler function which just calls plot.listof with equal.scales=TRUE.

o anova.ppm Output is neater.

o plot.layered New argument 'do.plot'

o plot.psp New argument 'do.plot'

o as.psp.owin New argument 'window'

o plot.im, contour.im, textureplot New argument 'clipwin'

o plot.ppp New argument 'clipwin'

o plot.msr New argument 'how' allows density to be plotted as image and/or contour

o diagnose.ppm, plot.diagppm More options for 'plot.neg'

o plot.leverage.ppm, plot.influence.ppm, plot.msr Argument 'clipwin' can now be used to restrict the display to a subset of the full data.

o [.hyperframe, [<-.hyperframe, $.hyperframe, $<-.hyperframe These functions are now documented.

o leverage.ppm, influence.ppm, dfbetas.ppm Resulting objects are now smaller (in memory size).

o print.ppm Now indicates whether the irregular parameters 'covfunargs' were optimised (by profilepl or ippm) or whether they were simply provided by the user.

o plot.ppp A point pattern with numerical marks can now be plotted as filled dots with colours determined by the marks, by setting pch=21 and bg=

o colourmap Now handles dates and date-time values (of class 'Date' or 'POSIXt').

o plot.ppp, print.ppp, summary.ppp Improved handling of dates and date-time values (of class 'Date' or 'POSIXt') in the marks of a point pattern.

o cut.im Now refuses to handle images whose pixel values are factor, logical or character.

o centroid.owin New argument 'as.ppp'

o superimpose Improved default names for columns of marks.

o Softcore() Improved printout.

o kppm, lgcp.estpcf, lgcp.estK Adjusted to new structure of RandomFields package. No change in syntax.

o data(murchison) This dataset now belongs to class 'listof' so that it can be plotted directly.

o data(clmfires) The format of the covariate data has changed. The objects 'clmcov100' and 'clmcov200' are now elements of a list 'clmfires.extra'.

o bounding.box This function is now Deprecated; it has been replaced by the generic boundingbox().

o as.psp.owin This function is now Deprecated; it has been replaced and extended by the function edges().

o plot.kstest Changed defaults so that the two curves are distinguishable.

o with.fv Improved mathematical labels.

BUG FIXES

o intensity.quadratcount Values were incorrect for a rectangular tessellation (the matrix of intensities was transposed). Fixed.

o rmh, simulate.ppm Simulation of the Strauss-hard core model (StraussHard) was incorrect (intensity of the simulated process was about 15% too low). Bug introduced in spatstat 1.31-0 (January 2013).

o intensity.quadratcount Crashed for a rectangular tessellation with only a single row or column. Fixed.

o model.images.ppm Crashed sometimes if the argument W was given. Fixed.

o eval.im Crashed when applied to images with only a single row or column. Fixed.

o ppp, marks<-.ppp If the marks were a vector of dates, they were erroneously converted to numbers. Fixed.

o ippm Crashed if the model formula included an offset term that was not a function. Fixed.

o leverage.ppm Crashed sometimes when the model had irregular parameters ('covfunargs'). Fixed.

o residuals.ppm Crashed sometimes when type='score'. Fixed.

o scaletointerval Did not handle dates and date-time values correctly. Fixed.

o rbind.hyperframe, as.list.hyperframe Gave incorrect results for hyperframes with 1 row. Fixed.

o Kinhom Did not renormalise the result (even when renormalise=TRUE), in some cases. Spotted by Peter Forbes. Fixed.

o disc If mask=TRUE the disc was erroneously clipped to the square [-1,1] x [-1,1]. Fixed.

o plot.fv Sometimes shaded the wrong half of the graph when the 'shade' coordinates were infinite. Fixed.

o print.ppm Gave an error message if the coefficient vector had length zero. Fixed.

o vcov.ppm Gave an error message if the coefficient vector had length zero. Fixed.

o plot.distfun, as.im.distfun These functions effectively ignored the argument 'invert' in the original call to distfun. Fixed.

o plot.msr Ignored certain additional arguments such as 'pch'. Fixed.

o cut.im Crashed if the image had 1 row or 1 column of pixels. Fixed.

o iplot.ppp Crashed with message about missing object 'vals'. Fixed.

o effectfun Demanded a value for every covariate supplied in the original call to ppm, even for covariates which were not used in the model. Fixed.

o plot.listof, plot.hyperframe When plotting 3D point patterns (class pp3), these functions issued warnings about 'add' being an unrecognised graphics argument. Fixed.

```
CHANGES IN spatstat VERSION 1.36-0
```

OVERVIEW

o We thank Sebastian Meyer, Kevin Ummer, Jean-Francois Coeurjolly, Ege Rubak, Rasmus Waagepetersen, Oscar Garcia and Sourav Das for contributions.

o Important change to package dependencies.

o Geometrical inconsistencies in polygons are now repaired automatically.

o Improved quadrature schemes and reduced bias in ppm.

o New vignette 'Summary of Recent Changes to Spatstat'.

o Approximation to K function and pcf for Gibbs models.

o Counterpart of 'apply' for lists of images.

o Hexagonal grids and tessellations.

o Extensions to scan test and Allard-Fraley cluster set estimator.

o Change the parameters of a fitted model before simulating it.

o Accelerated Kest, Kinhom for rectangular windows.

o Extensions and improvements to plotting functions.

o Improvements to labelling of 'fv' objects.

o New demo of summary functions.

o More methods for 'intensity'.

o Version nickname: 'Intense Scrutiny'

NEW FUNCTIONS

o Kmodel.ppm, pcfmodel.ppm Compute approximation to K-function or pair correlation function of a Gibbs point process model.

o im.apply Apply a function to corresponding pixel values in several images.

o hexgrid, hextess Create a hexagonal grid of points, or a tessellation of hexagonal tiles

o shift.tess, rotate.tess, reflect.tess, scalardilate.tess, affine.tess Apply a geometrical transformation to a tessellation.

o quantile.ewcdf Extract quantiles from a weighted cumulative distribution function.

o scanLRTS Evaluate the spatially-varying test statistic for the scan test.

o pcfmulti General multitype pair correlation function

o intensity.splitppp Estimate intensity in each component of a split point pattern.

o intensity.quadratcount Use quadrat counts to estimate intensity in each quadrat.

o as.owin.quadratcount, as.owin.quadrattest Extract the spatial window in which quadrat counts were performed.

o reload.or.compute Utility function for R scripts: either reload results from file, or compute them.

o to.grey Convert colour to greyscale.

o Smooth.im Method for Smooth() for pixel images. Currently identical to blur().

o demo(sumfun) Demonstration of nonparametric summary functions in spatstat.

SIGNIFICANT USER-VISIBLE CHANGES

o Package Dependencies spatstat now "Imports" (rather than "Depends" on) the libraries mgcv, deldir, abind, tensor, polyclip. This means that these libraries are not accessible to the user unless the user explicitly loads them by typing 'library(mgcv)' and so on.

o owin, as.owin Polygon data are no longer subjected to strict checks on geometrical validity (self-crossing points, overlaps etc.) Instead, polygon geometry is automatically repaired.

o ppm The default quadrature scheme for a point pattern has been improved (in the case of a non-rectangular window) to remove a possible source of bias.

o Performance various parts of spatstat now run slightly faster.

o scan.test Now handles multiple values of circle radius 'r'.

o plot.scan.test, as.im.scan.test These functions can now give the optimal value of circle radius 'r'.

o pcfcross, pcfdot Algorithms have been reimplemented using a single-pass kernel smoother and now run much faster. Bandwidth selection rule improved.

o plot.listof, plot.splitppp Default behaviour has changed: panels are now plotted on different scales.

o plot.listof, plot.splitppp When 'equal.scales=TRUE' the panels are plotted on exactly equal scales and are exactly aligned (under certain conditions).

o ppp, marks.ppp, marks<-.ppp New argument 'drop' determines whether a data frame with a single column will be converted to a vector.

o simulate.ppm, rmh.ppm, rmhmodel.ppm New argument 'new.coef' allows the user to change the parameters of a fitted model, before it is simulated.

o logLik.ppm New argument 'new.coef' allows the user to evaluate the loglikelihood for a different value of the parameter.

o clusterset The argument 'result' has been renamed 'what'. It is now possible to give multiple values to 'what' so that both types of result can be computed together.

o residuals.ppm Argument 'coefs' has been renamed 'new.coef' for consistency with fitted.ppm etc.

o residuals.ppm If drop=TRUE the window associated with the residuals is now taken to be the domain of integration of the composite likelihood.

o intensity.ppp Now has argument 'weights'

o density.ppp, Smooth.ppp, markmean, markvar, intensity.ppp Argument 'weights' can now be an 'expression'.

o pcf New argument 'domain' causes the computation to be restricted to a subset of the window.

o nnclean The result now has attributes which give the fitted parameter values, information about the fitting procedure, and the histogram bar heights.

o nnclean Extra arguments are now passed to hist.default.

o plot.tess For a tessellation represented by a pixel image, plot.tess no longer treats the pixel labels as palette colours.

o relrisk New argument 'case' allows the user to specify which mark value corresponds to the cases in a case-control dataset.

o Kinhom Now accepts correction="good"

o spatstat.options New option ('monochrome') controls whether plots generated by spatstat will be displayed in colour or in greyscale. This will eventually be applied to all plot commands in spatstat.

o plot.im, persp.im, contour.im, plot.owin, plot.psp, plot.fv, plot.fasp These functions now obey spatstat.options('monochrome')

o plot.ppp, plot.owin, plot.im, plot.psp, plot.tess, plot.layered New universal argument 'show.all' determines what happens when a plot is added to an existing plot. If show.all = TRUE then everything is plotted, including the main title and colour ribbon.

o plot.ppp New argument 'show.window'

o plot.im New arguments 'add' and 'do.plot'. More arguments recognised by 'ribargs'

o plot.layered New arguments 'add', 'main' Better argument handling.

o plot.fv Improved handling of argument 'shade'

o layered, layerplotargs, plot.layered The plotting argument can now be a list of length 1, which will be replicated to the correct length.

o varblock Ugly legends have been repaired.

o quad.ppm New argument 'clip'

o edge.Trans New arguments 'dx', 'dy'

o disc Argument 'centre' can be in various formats.

o affine, shift Argument 'vec' can be in various formats.

o Geyer, BadGey A warning is no longer issued when the parameter 'sat' is fractional.

o adaptive.density Now has argument 'verbose'

o Smooth.ppp 'sigma' is now a formal argument of Smooth.ppp

o plot.quadratcount, plot.quadrattest These functions have now been documented.

o Summary functions and envelopes Improved mathematical labels in plots.

o Kest Accelerated, in the case of a rectangular window.

o Kscaled Argument 'lambda' can now be a fitted model (class ppm)

o print.fv Improved layout.

o plot.bermantest Improved graphics.

o which.max.im This function is now deprecated. which.max.im(x) is superseded by im.apply(x, which.max)

o smooth.ppp, smooth.fv, smooth.msr These functions are now deprecated, in favour of 'Smooth' with a capital 'S'

BUG FIXES

o bw.ppl Crashed if the point pattern had multiple points at the same location. Fixed.

o quantile Crashed when applied to the result of 'ewcdf'. Fixed.

o marks<-.ppp Crashed with a message about 'unrecognised format' if the current or replacement values of marks were date/time values (belonging to class 'Date' or 'POSIXt'). Fixed.

o plot.im Crashed in case log=TRUE if the window was not a rectangle. Fixed.

o vcov.ppm Crashed sometimes for models with a hard core term (Hardcore, StraussHard, MultiHard or MultiStrauss interactions). Spotted by Rasmus Waagepetersen. Fixed.

o multiplicity.data.frame Results were incorrect and included NA's (spotted by Sebastian Meyer). Fixed.

o markvar Values were incorrect. Fixed.

o Smooth.ppp Ignored argument 'diggle'. Fixed.

o rotate.im, affine.im Factor-valued images were not handled correctly. Fixed.

o shift.layered If argument 'origin' was used, different layers were shifted by different amounts. Fixed.

o tile.areas Sometimes returned a list instead of a numeric vector. Fixed.

o print.ppp If the marks were date/time values (belonging to class 'Date' or 'POSIXt'), print.ppp reported that they were double precision numbers. Fixed.

o plot.layered Graphics were mangled if the argument 'add=FALSE' was given explicitly. Fixed.

o Smooth.ppp The argument 'sigma' was only recognised if it was explicitly named. For example in 'Smooth(X, 5)' the '5' was ignored. Fixed.

o clusterset The bounding frame of the result was smaller than the original bounding frame of the point pattern dataset, when result="domain" and exact=TRUE. Fixed.

o plot.im Ignored argument 'col' if it was a 'function(n)'. Fixed.

o Kinhom Ignored argument 'correction' if there were more than 1000 points. Fixed.

o [.fv Mangled the plot label for the y axis. Fixed.

o cbind.fv Mangled the plot label for the y axis. Fixed.

o plot.envelope Main title was always 'x'. Fixed.

o print.ppp Ran over the right margin. Fixed.

o union.owin, intersect.owin, setminus.owin Sometimes deleted the name of the unit of length. Fixed.

```
CHANGES IN spatstat VERSION 1.35-0
```

OVERVIEW

o We thank Melanie Bell, Leanne Bischof, Ida-Maria Sintorn, Ege Rubak, Martin Hazelton, Oscar Garcia, Rasmus Waagepetersen, Abdollah Jalilian and Jens Oehlschlaegel for contributions.

o Support for analysing replicated spatial point patterns.

o New vignette on analysing replicated spatial point patterns.

o Objective function surface plots.

o Estimator of point process intensity using nearest neighbour distances.

o Improved estimator of pair correlation function.

o Four new datasets.

o Simple point-and-click interface functions for general use.

o More support for fv objects.

o More support for ppx objects.

o Extensions to nearest neighbour functions.

o Morphological operations accelerated.

o Bug fix to pair correlation functions.

o Bug fix to k-th nearest neighbour distances

o Version nickname: 'Multiple Personality'

NEW CLASSES

o mppm An object of class 'mppm' represents a Gibbs point process model fitted to several point pattern datasets. The point patterns may be treated as independent replicates of the same point process, or as the responses in an experimental design, so that the model may depend on covariates associated with the design. Methods for this class include print, plot, predict, anova and so on.

o objsurf An object of class 'objsurf' contains values of the likelihood or objective function in a neighbourhood of the maximum.

o simplepanel An object of class 'simplepanel' represents a spatial arrangement of buttons that respond to mouse clicks, supporting a simple, robust graphical interface.

NEW FUNCTIONS

o mppm Fit a Gibbs model to several point patterns. The point pattern data may be organised as a designed experiment and the model may depend on covariates associated with the design.

o anova.mppm Analysis of Deviance for models of class mppm

o coef.mppm Extract fitted coefficients from a model of class mppm

o fitted.mppm Fitted intensity or conditional intensity for a model of class mppm

o kstest.mppm Kolmogorov-Smirnov test of goodness-of-fit for a model of class mppm

o logLik.mppm log likelihood or log pseudolikelihood for a model of class mppm

o plot.mppm Plot the fitted intensity or conditional intensity of a model of class mppm

o predict.mppm Compute the fitted intensity or conditional intensity of a model of class mppm

o quadrat.test Quadrat counting test of goodness-of-fit for a model of class mppm

o residuals.mppm Point process residuals for a model of class mppm

o subfits Extract point process models for each individual point pattern dataset, from a model of class mppm

o vcov.mppm Variance-covariance matrix for a model of class mppm

o integral.msr Integral of a measure.

o objsurf For a model fitted by optimising an objective function, this command computes the objective function in a neighbourhood of the optimal value.

o contour.objsurf, image.objsurf, persp.objsurf, plot.objsurf Plot an 'objsurf' object.

o fvnames Define groups of columns in a function value table, for use in plot.fv, etc

o multiplicity New generic function for which multiplicity.ppp is a method.

o unique.ppx, duplicated.ppx, multiplicity.ppx Methods for unique(), duplicated() and multiplicity() for 'ppx' objects. These also work for 'pp3' and 'lpp' objects.

o closepairs, crosspairs, closepaircounts, crosspaircounts Low-level functions for finding all close pairs of points

o nndensity Estimate point process intensity using k-th nearest neighbour distances

o simplepanel, run.simplepanel Support for a simple point-and-click interface for general use.

NEW DATASETS

o pyramidal Diggle-Lange-Benes data on pyramidal neurons in cingulate cortex. 31 point patterns divided into 3 groups.

o waterstriders Nummelin-Penttinen waterstriders data. Three independent replicates of a point pattern formed by insects.

o simba Simulated data example for mppm. Two groups of point patterns with different interpoint interactions.

o demohyper Simulated data example for mppm. Point patterns and pixel image covariates, in two groups with different regression coefficients.

SIGNIFICANT USER-VISIBLE CHANGES

o plot.hyperframe The argument 'e' now has a different format. Instead of plot(h, plot(XYZ)) one must now type plot(h, quote(plot(XYZ))) This is necessary in order to avoid problems with 'S4 method dispatch'.

o pcf.ppp, pcfinhom New argument 'divisor' enables better performance of the estimator of pair correlation function for distances close to zero.

o applynbd The arguments N, R and criterion may now be specified together.

o markstat The arguments N and R may now be specified together.

o ppx New argument 'simplify' allows the result to be converted to an object of class 'ppp' or 'pp3' if appropriate.

o as.function.fv Now allows multiple columns to be interpolated

o multiplicity.ppp This function is now a method for the generic 'multiplicity'. It has also been accelerated.

o nnfun.ppp, distfun.ppp New argument 'k' allows these functions to compute k-th nearest neighbours.

o rVarGamma, kppm, vargamma.estK, vargamma.estpcf New argument 'nu.pcf' provides an alternative way to specify the kernel shape in the VarGamma model, instead of the existing argument 'nu.ker'. Function calls that use the ambiguous argument name 'nu' will no longer be accepted.

o nnmap Image is now clipped to the original window.

o dilation, erosion, opening, closing Polygonal computations greatly accelerated.

o plot.colourmap Improved appearance and increased options, for discrete colourmaps.

o plot.msr Improved appearance

o plot.ppp, plot.owin An `empty' plot can now be generated by setting type="n"

o nndist.ppp, nnwhich.ppp, nncross.ppp Column names of the result are now more informative.

BUG FIXES

o nncross.ppp Results were completely incorrect when k > 1. Spotted by Jens Oehschlaegel. Bug was introduced in spatstat 1.34-1. Fixed.

o rVarGamma
Simulations were incorrect; they were generated using the wrong value
of the parameter 'nu.ker'. Spotted by Rasmus Waagepetersen and
Abdollah Jalilian. Bug was always present.

Fixed.

o pair correlation functions (pcf.ppp, pcfdot, pcfcross, pcfinhom, ...) The result had a negative bias at the maximum 'r' value, because contributions to the pcf estimate from interpoint distances greater than max(r) were mistakenly omitted. Spotted by Rasmus Waagepetersen and Abdollah Jalilian. Bug was always present. Fixed.

o demo(spatstat) This demonstration script had some unwanted side-effects, such as rescaling the coordinates of standard datasets 'bramblecanes', 'amacrine' and 'demopat', which caused the demonstration to crash when it was repeated several times, and caused errors in demo(data). Fixed.

o rmh Visual debugger crashed sometimes with message 'XI not found'. Fixed.

o predict.ppm Crashed if the model was fitted using 'covfunargs'. Fixed.

o bounding.box Crashed if one of the arguments was NULL. Fixed.

o multiplicity.ppp Did not handle data frames of marks. Fixed.

```
CHANGES IN spatstat VERSION 1.34-1
```

OVERVIEW

o We thank Kurt Hornik, Ted Rosenbaum, Ege Rubak and Achim Zeileis for contributions.

o Important bug fix.

SIGNIFICANT USER-VISIBLE CHANGES

o as.box3 Now accepts objects of class 'ppx' or 'boxx'.

o crossdist.ppp, crossdist.pp3, crossdist.default New argument 'squared' allows the squared distances to be computed (saving computation time in some applications)

BUG FIXES

o union.owin, is.subset.owin, dilation.owin Results were sometimes completely wrong for polygons with holes. Spotted by Ted Rosenbaum. Fixed.

o psstA, areaLoss Crashed in some cases, with error message 'Number of items to replace is not a multiple of replacement length'. Spotted by Achim Zeileis. Fixed.

```
CHANGES IN spatstat VERSION 1.34-0
```

OVERVIEW

o We thank Andrew Bevan, Ege Rubak, Aruna Jammalamadaka, Greg McSwiggan, Jeff Marcus, Jose M Blanco Moreno, and Brian Ripley for contributions.

o spatstat and all its dependencies are now Free Open Source.

o spatstat does not require the package 'gpclib' any more.

o spatstat now depends on the packages 'tensor', 'abind' and 'polyclip'

o polygon clipping is now enabled always.

o Substantially more support for point patterns on linear networks.

o Faster computations for pairwise interaction models.

o Bug fixes in nearest neighbour calculations.

o Bug fix in leverage and influence diagnostics.

o Version nickname: "Window Cleaner"

o spatstat now requires R version 3.0.2 or later

NEW FUNCTIONS

o as.lpp Convert data to a point pattern on a linear network.

o distfun.lpp Distance function for point pattern on a linear network.

o eval.linim Evaluate expression involving pixel images on a linear network.

o linearKcross, linearKdot, linearKcross.inhom, linearKdot.inhom Multitype K functions for point patterns on a linear network

o linearmarkconnect, linearmarkequal Mark connection function and mark equality function for multitype point patterns on a linear network

o linearpcfcross, linearpcfdot, linearpcfcross.inhom, linearpcfdot.inhom Multitype pair correlation functions for point patterns on a linear network

o linfun New class of functions defined on a linear network

o nndist.lpp, nnwhich.lpp, nncross.lpp Methods for nndist, nnwhich, nncross for point patterns on a linear network

o nnfun.lpp Method for nnfun for point patterns on a linear network

o vcov.lppm Variance-covariance matrix for parameter estimates of a fitted point process model on a linear network.

o bilinearform Computes a bilinear form

o tilenames, tilenames<- Extract or change the names of tiles in a tessellation.

SIGNIFICANT USER-VISIBLE CHANGES

o package dependencies Previous versions of spatstat used the package 'gpclib' to perform geometrical calculations on polygons. Spatstat now uses the package 'polyclip' for polygon calculations instead.

o free open-source licence The restrictive licence conditions of 'gpclib' no longer apply to users of spatstat. Spatstat and all its dependencies are now covered by a free open-source licence.

o polygon clipping In previous versions of spatstat, geometrical calculations on polygons could be performed 'exactly' using gpclib or 'approximately' using pixel discretisation. Polygon calculations are now always performed 'exactly'.

o intersect.owin, union.owin, setminus.owin If A and B are polygons, the result is a polygon.

o erosion, dilation, opening, closing If the original set is a polygon, the result is a polygon.

o intersect.tess, dirichlet The tiles of the resulting tessellation are polygons if the input was polygonal.

o plot.owin Polygons with holes can now be plotted with filled colours on any device.

o lppm New arguments 'eps' and 'nd' control the quadrature scheme.

o pairwise interaction Gibbs models Many calculations for these models have been accelerated.

BUG FIXES

o nncross.pp3 Values were completely incorrect in some cases. Usually accompanied by a warning about NA values. (Spotted by Andrew Bevan.) Fixed.

o nnmap, nnmark A small proportion of pixels had incorrect values. [These were the pixels lying on the boundary of a Dirichlet cell.] Fixed.

o leverage.ppm, influence.ppm, dfbetas.ppm Results were incorrect for non-Poisson processes. Fixed.

o distcdf Results were incorrect in some cases when W was a window and V was a point pattern. Fixed.

o Kcross, Kdot, pcfcross, pcfdot Results were incorrect in some rare cases. Fixed.

o as.fv.kppm Erroneously returned a NULL value. Fixed.

o vcov.ppm For point process models fitted with method = 'logi', sometimes crashed with error "object 'fit' not found". (Spotted by Ege Rubak). Fixed.

o vcov.ppm For multitype point process models, sometimes crashed with error "argument 'par' is missing". Fixed.

o plot.im Crashed if some of the pixel values were infinite. Fixed.

o owin owin(poly=..) crashed if there were NA's in the polygon coordinates. Spotted by Jeff Marcus. Fixed.

o plot.fv Crashed, giving an incomprehensible error, if the plot formula contained a number with a decimal point. Fixed.

o alltypes Crashed if envelopes=TRUE and global=TRUE, with error message 'csr.theo not found'. Spotted by Jose M Blanco Moreno. Fixed.

o chop.tess, rMosaicField Format of result was garbled in some cases. Fixed.

o vcov.ppm Sometimes gave an irrelevant warning "parallel option not available". Fixed.

```
CHANGES IN spatstat VERSION 1.33-0
```

OVERVIEW

o We thank Kurt Hornik and Brian Ripley for advice.

o The package namespace has been modified.

o Numerous internal changes.

o Likelihood cross-validation for smoothing bandwidth.

o More flexible models of intensity in cluster/Cox processes.

o New generic function for smoothing.

o Version nickname: 'Titanic Deckchair'

NEW FUNCTIONS

```
o bw.ppl
Likelihood cross-validation technique
for bandwidth selection in kernel smoothing.
o is.lppm, is.kppm, is.slrm
Tests whether an object is of class 'lppm', 'kppm' or 'slrm'
o Smooth
New generic function for spatial smoothing.
o Smooth.ppp, Smooth.fv, Smooth.msr
Methods for Smooth
(identical to smooth.ppp, smooth.fv, smooth.msr respectively)
o fitted.kppm
Method for 'fitted' for cluster/Cox models
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o namespace
The namespace of the spatstat package has been changed.
o internal functions
Some undocumented internal functions are no longer visible,
as they are no longer exported in the namespace. These functions
can still be accessed using the form spatstat:::functionname.
Functions that are not visible are not guaranteed to exist
or to remain the same in future.
o methods
For some generic functions defined in the spatstat package,
it is possible that R may fail to find one of the methods
for the generic. This is a temporary problem due to a restriction
on the size of the namespace in R 3.0.1. It will be fixed in
future versions of R and spatstat. It only applies to methods
for a generic which is a spatstat function (such as nndist)
and does not apply to methods for generics defined elsewhere
(such as density). In the meantime, if this problem should occur,
it can be avoided by calling the method explicitly, in the form
spatstat:::genericname.classname.
o speed
The package should run slightly faster overall, due to the
improvement of the namespace, and changes to internal code.
o envelope
New argument 'envir.simul' determines the environment
in which to evaluate the expression 'simulate'.
o kppm
More flexible models of the intensity, and greater control over the
intensity fitting procedure, are now possible using the arguments
'covfunargs', 'use.gam', 'nd', 'eps' passed to ppm.
Also the argument 'X' may now be a quadrature scheme.
o distcdf
Arguments W and V can now be point patterns.
o Kest
New option: correction = "good"
selects the best edge correction that can be computed in reasonable time.
o bw.diggle
Accelerated.
o predict.ppm
Calculation of standard error has been accelerated.
o smooth.ppp, smooth.fv, smooth.msr
These functions will soon be 'Deprecated' in favour of
the methods Smooth.ppp, Smooth.fv, Smooth.msr respectively.
o stratrand, overlap.owin, update.slrm, edge.Trans, edge.Ripley
These already-existing functions are now documented.
```

BUG FIXES

```
o kppm, matclust.estpcf, pcfmodel
The pair correlation function of the Matern Cluster Process
was evaluated incorrectly at distances close to 0.
This could have affected the fitted parameters
in matclust.estpcf() or kppm(clusters="MatClust").
Fixed.
o anova.ppm
Would cause an error in future versions of R
when 'anova.glm' is removed from the namespace.
Fixed.
CHANGES IN spatstat VERSION 1.32-0
```

OVERVIEW

o We thank Ege Rubak for major contributions.

o Thanks also to Patrick Donnelly, Andrew Hardegen, Tom Lawrence, Robin Milne, Gopalan Nair and Sean O'Riordan.

o New 'logistic likelihood' method for fitting Gibbs models.

o Substantial acceleration of several functions including profile maximum pseudolikelihood and variance calculations for Gibbs models.

o Nearest neighbours for point patterns in 3D

o Nearest-neighbour interpolation in 2D

o New 'progress plots'

o Hard core thresholds can be estimated automatically.

o More support for colour maps

o More support for 'fv' objects

o Spatstat now has version nicknames. The current version is "Logistical Nightmare".

o Minor improvements and bug fixes.

NEW FUNCTIONS

o nncross.pp3 Method for 'nncross' for point patterns in 3D

o nnmark Mark of nearest neighbour - can be used for interpolation

o dclf.progress, mad.progress Progress plots (envelope representations) for the DCLF and MAD tests.

o deriv.fv Numerical differentiation for 'fv' objects.

o interp.colourmap Smooth interpolation of colour map objects - makes it easy to build colour maps with gradual changes in colour

o tweak.colourmap Change individual colour values in a colour map object

o beachcolourmap Colour scheme appropriate for `altitudes' (signed numerical values)

o as.fv Convert various kinds of data to an 'fv' object

o quadscheme.logi Generates quadrature schemes for the logistic method of ppm.

o beginner Introduction for beginners.

SIGNIFICANT USER-VISIBLE CHANGES

o ppm New option: method = "logi" Fits a Gibbs model by the newly developed 'logistic likelihood' method which is often faster and more accurate than maximum pseudolikelihood. Code contributed by Ege Rubak.

o profilepl Greatly accelerated, especially for area-interaction models.

o vcov.ppm Greatly accelerated for higher-order interaction models.

o smooth.ppp Now handles bandwidths equal to zero (by invoking 'nnmark')

o Hardcore, StraussHard The hard core distance 'hc' can now be omitted; it will be estimated from data.

o plot.ppp Now behaves differently if there are multiple columns of marks. Each column of marks is plotted, in a series of separate plots arranged side-by-side.

o plot.im Argument 'col' can now be a function

o lohboot Now computes confidence intervals for L-functions as well (fun="Lest" or fun="Linhom")

o dclf.test, mad.test The argument X can now be an object produced by a previous call to dclf.test or mad.

o plot.fv Labelling of plots has been improved in some cases.

o smooth.fv Further options added.

o density.ppp The argument 'weights' can now be a matrix.

o smooth.ppp Accelerated, when there are several columns of marks.

o density.ppp Accelerated slightly.

o simulate.ppm, simulate.kppm The total computation time is also returned.

o simulate.kppm Now catches errors (such as 'insufficient memory').

o latest.news, licence.polygons Can now be executed by typing the name of the function without parentheses.

o latest.news The text is now displayed one page at a time.

BUG FIXES

o Hest, Gfox, Jfox The 'raw' estimate was not computed correctly (or at least it was not the raw estimate described in the help files). Spotted by Tom Lawrence. Fixed.

o edges2vees Format of result was incorrect if there were fewer than 3 edges. Fixed.

o Jfox The theoretical value (corresponding to independence between X and Y) was erroneously given as 0 instead of 1. Spotted by Patrick Donnelly. Fixed.

o ppm, quadscheme, default.dummy If the grid spacing parameter 'eps' was specified, the quadrature scheme was sometimes slightly incorrect (missing a few dummy points near the window boundary). Fixed.

o print.timed Matrices were printed incorrectly. Fixed.

```
CHANGES IN spatstat VERSION 1.31-3
```

OVERVIEW

o spatstat now 'Suggests' the package 'tensor'

o Code slightly accelerated.

o More support for pooling of envelopes.

o Bug fixes.

NEW FUNCTIONS

o nnmap Given a point pattern, finds the k-th nearest point in the pattern from each pixel in a raster.

o coef.fii, coef.summary.fii Extract the interaction coefficients of a fitted interpoint interaction

o edges2vees Low-level function for finding triples in a graph.

SIGNIFICANT USER-VISIBLE CHANGES

o predict.ppm New argument 'correction' allows choice of edge correction when calculating the conditional intensity.

o pool.envelope New arguments 'savefuns' and 'savepatterns'.

o pool.envelope Envelopes generated with VARIANCE=TRUE can now be pooled.

o pool.envelope The plot settings of the input data are now respected.

o Numerous functions have been slightly accelerated.

BUG FIXES

o predict.ppm Calculation of the conditional intensity omitted the edge correction if correction='translate' or correction='periodic'. Fixed.

o shift.lpp, rotate.lpp, scalardilate.lpp, affine.lpp, shift.linnet, rotate.linnet, scalardilate.linnet, affine.linnet The enclosing window was not correctly transformed. Fixed.

o rHardcore, rStraussHard, rDiggleGratton, rDGS The return value was invisible. Fixed.

o ppm In rare cases the results obtained with forcefit=FALSE and forcefit=TRUE were different, due to numerical rounding effects. Fixed.

```
CHANGES IN spatstat VERSION 1.31-2
```

OVERVIEW

o We thank Robin Corria Anslie, Julian Gilbey, Kiran Marchikanti, Ege Rubak and Thordis Linda Thorarinsdottir for contributions.

o spatstat now depends on R 3.0.0

o More support for linear networks

o More functionality for nearest neighbours

o Bug fix in fitting Geyer model

o Performance improvements and bug fixes

NEW FUNCTIONS

o affine.lpp, shift.lpp, rotate.lpp, rescale.lpp, scalardilate.lpp Geometrical transformations for point patterns on a linear network

o affine.linnet, shift.linnet, rotate.linnet, rescale.linnet, scalardilate.linnet Geometrical transformations for linear networks

o [.linnet Subset operator for linear networks

o timed Records the computation time taken

SIGNIFICANT USER-VISIBLE CHANGES

o nncross nncross.ppp can now find the k-th nearest neighbours, for any k.

o nndist, nnwhich New argument 'by' makes it possible to find nearest neighbours belonging to specified subsets in a point pattern, for example, the nearest neighbour of each type in a multitype point pattern.

o [.fv Now handles the argument 'drop'.

o with.fv Argument 'drop' replaced by new argument 'fun' (with different interpretation).

o [.lpp Subset index may now be a window (class 'owin')

o Kest Options correction='border' and correction='none' now run about 4 times faster, thanks to Julian Gilbey.

o density.ppp Numerical underflow no longer occurs when sigma is very small and 'at="points"'. A warning is no longer issued. Thanks to Robin Corria Anslie.

o crossing.psp New argument 'fatal' allows the user to handle empty intersections

o union.owin It is now guaranteed that if A is a subset of B, then union.owin(A,B)=B.

o plot.colourmap Now passes arguments to axis() to control the plot. Appearance of plot improved.

o image.listof Now passes arguments to plot.colourmap() if equal.ribbon=TRUE.

o kppm Accelerated (especially for large datasets).

o plot.envelope plot.envelope is now equivalent to plot.fv and is essentially redundant.

o rThomas, rMatClust, rNeymanScott Improved explanations in help files.

o All functions Many functions have been slightly accelerated.

BUG FIXES

o ppm Results were incorrect for the Geyer saturation model with a non-integer value of the saturation parameter 'sat'. Spotted by Thordis Linda Thorarinsdottir. Bug introduced in spatstat 1.20-0, July 2010. Fixed.

o ppm Fitting a stationary Poisson process using a nonzero value of 'rbord', as in "ppm(X, rbord=R)" with R > 0, gave incorrect results. Fixed.

o predict.slrm Crashed with message 'longer object length is not a multiple of shorter object length' if the original data window was not a rectangle. Fixed.

o iplot Main title was sometimes incorrect. Fixed.

o plot.layered Ignored argument 'main' in some cases. Fixed.

o plot.listof, image.listof Crashed sometimes with a message 'figure margins too large' when equal.ribbon=TRUE. Fixed.

o print.ppx Crashed if the object contained local coordinates. Fixed.

o transect.im Crashed if the transect lay partially outside the image domain. Fixed.

o rthin Crashed if X was empty. Fixed.

o max.im, min.im, range.im Ignored additional arguments after the first argument. Fixed.

o update.lppm Updated object did not remember the name of the original dataset. Fixed.

o envelope Grey shading disappeared from plots of envelope objects when the envelopes were transformed using eval.fv or eval.fasp. Fixed.

```
CHANGES IN spatstat VERSION 1.31-1
```

OVERVIEW

o We thank Marcelino de la Cruz, Daniel Esser, Jason Goldstick, Abdollah Jalilian, Ege Rubak and Fabrice Vinatier for contributions.

o Nonparametric estimation and tests for point patterns in a linear network.

o More support for 'layered' objects.

o Find clumps in a point pattern.

o Connected component interaction model.

o Improvements to interactive plots.

o Visual debugger for Metropolis-Hastings algorithm.

o Bug fix in Metropolis-Hastings simulation of Geyer process.

o Faster Metropolis-Hastings simulation.

o Faster computation of 'envelope', 'fv' and 'fasp' objects.

o Improvements and bug fixes.

NEW FUNCTIONS

o connected.ppp Find clumps in a point pattern.

o kstest.lpp, kstest.lppm The spatial Kolmogorov-Smirnov test can now be applied to point patterns on a linear network (class 'lpp') and point processes on a linear network (class 'lppm').

o bermantest.lpp, bermantest.lppm Berman's Z1 and Z2 tests can now be applied to point patterns on a linear network (class 'lpp') and point processes on a linear network (class 'lppm').

o rhohat.lpp, rhohat.lppm Nonparametric estimation of the dependence of a point pattern on a spatial covariate: 'rhohat' now applies to objects of class 'lpp' and 'lppm'.

o intensity.lpp Empirical intensity of a point pattern on a linear network.

o as.function.rhohat Converts a 'rhohat' object to a function, with extrapolation beyond the endpoints.

o [.layered Subset operator for layered objects.

o shift, rotate, affine, rescale, reflect, flipxy, scalardilate These geometrical transformations now work for 'layered' objects.

o iplot.layered Interactive plotting for 'layered' objects.

o as.owin.layered Method for as.owin for layered objects.

o [.owin Subset operator for windows, equivalent to intersect.owin.

o rcellnumber Generates random integers for the Baddeley-Silverman counterexample.

o is.lpp Tests whether an object is a point pattern on a linear network.

o is.stationary.lppm, is.poisson.lppm New methods for is.stationary and is.poisson for class 'lppm'

o sessionLibs Print library names and version numbers (for use in Sweave scripts)

SIGNIFICANT USER-VISIBLE CHANGES

o iplot iplot is now generic, with methods for 'ppp', 'layered' and 'default'. iplot methods now support zoom and pan navigation.

o rmh.default New argument 'snoop' allows the user to activate a visual debugger for the Metropolis-Hastings algorithm.

o connected connected() is now generic, with methods for 'im', 'owin' and 'ppp'.

o alltypes Now works for lpp objects

o rlabel Now works for lpp, pp3, ppx objects

o plot.kstest Can now perform P-P and Q-Q plots as well.

o plot.fasp New argument 'samey' controls whether all panels have the same y limits.

o plot.fasp Changed default value of 'samex'.

o Objects of class 'envelope', 'fv' and 'fasp' Reduced computation time and storage required for these objects.

o pcfmodel.kppm Improved calculation.

o plot.fv Improved collision-avoidance algorithm (for avoiding overlaps between curves and legend)

o ppm Improved error handling

o envelope All methods for 'envelope' now handle fun=NULL

o setminus.owin Better handling of the case where both arguments are rectangles.

o rmh Simulation has been further accelerated.

o lppm Accelerated.

o vcov.ppm Accelerated.

o marktable Accelerated.

o Triplets() interaction Accelerated.

o alltypes Accelerated when envelope=TRUE.

BUG FIXES

o rmh Simulation of the Geyer saturation process was incorrect. [Bug introduced in previous version, spatstat 1.31-0.] Fixed.

o rmh Simulation of the Geyer saturation process was incorrectly initialised, so that the results of a short run (i.e. small value of 'nrep') were incorrect, while long runs were correct. [Bug introduced in spatstat 1.17-0, october 2009.] Fixed.

o ppm Objects fitted with use.gam=TRUE caused fatal errors in various functions including print, summary, vcov and model.frame. Spotted by Jason Goldstick. Fixed.

o lpp, runiflpp, rpoislpp Empty point patterns caused an error. Fixed.

o rmh.default Crashed for hybrid models, with message 'Attempt to apply non-function'. Spotted by Ege Rubak. Fixed.

o relrisk Crashed when 'at="points"' for a multitype pattern with more than 2 types. Spotted by Marcelino de la Cruz. Fixed.

o erosion.owin, dilation.psp, border Ignored the arguments "..." in some cases (namely when the window was polygonal and 'gpclib' was disabled). Fixed.

o rsyst, rcell Did not correctly handle the argument 'dx'. Spotted by Fabrice Vinatier. Fixed.

o correction="trans" Various functions such as Kest no longer recognised 'correction = "trans"'. Fixed.

o istat Crashed with an error message about envelopes. Fixed.

o summary.ppm, print.ppm p-values which were exactly equal to zero were reported as NA. Fixed.

o [.im Crashed if the intersection consisted of a single row or column of pixels. Fixed.

o plot.im Sometimes incorrectly displayed an image consisting of a single row or column of pixels. Fixed.

o plot.layered The plot region was determined by the first layer, so that objects in subsequent layers could sometimes fall outside the plot region. Fixed.

o transect.im If the arguments 'from' and 'to' were numeric vectors of length 2, the result was garbled. Fixed.

o Inhomogeneous K functions and pair correlation functions [Kinhom, pcfinhom, Kcross.inhom, Kdot.inhom, pcfcross.inhom, etc.] These functions reported an error 'lambda is not a vector' if the intensity argument lambda was computed using density(, at="points"). Fixed.

o rlabel Did not accept a point pattern with a hyperframe of marks. Fixed.

o alltypes Crashed when envelope=TRUE if the summary function 'fun' did not have default values for the marks i and j. Fixed.

o Kres, Gres, psst, psstA Ignored the unit of length. Fixed.

```
CHANGES IN spatstat VERSION 1.31-0
```

OVERVIEW

o We thank Frederic Lavancier and Ege Rubak for contributions.

o Major bug fix in simulation of area-interaction process.

o Metropolis-Hastings simulations accelerated.

o Rounding of spatial coordinates

o clmfires dataset corrected.

o Bug fixes and minor improvements.

NEW FUNCTIONS

o round.ppp Round the spatial coordinates of a point pattern to a specified number of decimal places.

o rounding Determine whether a dataset has been rounded.

SIGNIFICANT USER-VISIBLE CHANGES

o rmh Simulation of the following models has been accelerated: areaint, dgs, diggra, fiksel, geyer, hardcore, lennard, multihard, strauss, straush, straussm, strausshm.

o rmh The transition history of the simulation (which is saved if 'track=TRUE') now also contains the value of the Hastings ratio for each proposal.

o clmfires The clmfires dataset has been modified to remove errors and inconsistencies.

o plot.linim Appearance of the plot has been improved, when style='width'.

o summary.ppm Now reports whether the spatial coordinates have been rounded.

o dclf.test, mad.test The range of distance values ('rinterval') used in the test is now printed in the test output, and is saved as an attribute.

BUG FIXES

o rmh Simulation of the Area-Interaction model was completely incorrect. Spotted by Frederic Lavancier. The bug was introduced in spatstat version 1.23-6 or later. Fixed.

o dclf.test The test statistic was incorrectly scaled (by a few percent). This did not affect the p-value of the test. Fixed.

o ppx If argument 'coord.type' was missing, various errors occurred: a crash may have occurred, or the results may have depended on the storage type of the data. Spotted by Ege Rubak. Fixed.

o plot.ppx Crashed for 1-dimensional point patterns. Spotted by Ege Rubak. Fixed.

```
CHANGES IN spatstat VERSION 1.30-0
```

OVERVIEW

o We thank Jorge Mateu, Andrew Bevan, Olivier Flores, Marie-Colette van Lieshout, Nicolas Picard and Ege Rubak for contributions.

o The spatstat manual now exceeds 1000 pages.

o Hybrids of point process models.

o Five new datasets

o Second order composite likelihood method for kppm.

o Inhomogeneous F, G and J functions.

o Delaunay graph distance

o Fixed serious bug in 'lppm' for marked patterns.

o bug fix in some calculations for Geyer model

o Improvements to linear networks code

o Pixel images can now be displayed with a logarithmic colour map.

o spatstat now formally 'Depends' on the R core package 'grDevices'

o miscellaneous improvements and bug fixes

NEW DATASETS

o clmfires Forest fires in Castilla-La Mancha

o gordon People sitting on the grass in Gordon Square, London

o hyytiala Mixed forest in Hyytiala, Finland (marked by species)

o paracou Kimboto trees in Paracou, French Guiana (marked as adult/juvenile)

o waka Trees in Waka national park (marked with diameters)

NEW FUNCTIONS

o Hybrid The hybrid of several point process interactions [Joint research with Jorge Mateu and Andrew Bevan]

o is.hybrid Recognise a hybrid interaction or hybrid point process model.

o Finhom, Ginhom, Jinhom Inhomogeneous versions of the F, G and J functions [Thanks to Marie-Colette van Lieshout]

o delaunay.distance Graph distance in the Delaunay triangulation.

o distcdf Cumulative distribution function of the distance between two independent random points in a given window.

o bw.frac Bandwidth selection based on window geometry

o shortside.owin, sidelengths.owin Side lengths of (enclosing rectangle of) a window

SIGNIFICANT USER-VISIBLE CHANGES

o ppm Can now fit models with 'hybrid' interactions [Joint research with Jorge Mateu and Andrew Bevan]

o kppm Now has the option of fitting models using Guan's (2006) second order composite likelihood.

o envelope.lpp Now handles multitype point patterns.

o envelope.envelope New argument 'transform' allows the user to apply a transformation to previously-computed summary functions.

o runifpointOnLines, rpoisppOnLines, runiflpp, rpoislpp Can now generate multitype point patterns.

o rmhmodel, rmh, simulate.ppm Now handle point process models with 'hybrid' interactions.

o kppm Accelerated, and more reliable, due to better choice of starting values in the optimisation procedure.

o kppm The internal format of kppm objects has changed.

o minimum contrast estimation Error messages from the optimising function 'optim' are now trapped and handled.

o rhohat This command is now generic, with methods for ppp, quad, and ppm.

o raster.x, raster.y, raster.xy These functions have a new argument 'drop'

o summary.ppm Improved behaviour when the model covariates are a data frame.

o progressreport Output improved.

o second order summary functions (Kest, Lest, Kinhom, pcf.ppp, Kdot, Kcross, Ldot etc etc) These functions now accept correction="translation" as an alternative to correction = "translate", for consistency.

o plot.im New argument 'log' allows colour map to be equally spaced on a log scale.

o as.owin.ppm, as.owin.kppm New argument 'from' allows the user to extract the spatial window of the point data (from="points") or the covariate images (from="covariates")

o dclf.test, mad.test The rule for handling tied values of the test statistic has been changed. The tied values are now randomly ordered to obtain a randomised integer rank.

o with.fv New argument 'enclos' allows evaluation in other environments

BUG FIXES

o lppm For multitype patterns, the fitted model was completely incorrect due to an error in constructing the quadrature scheme. Fixed.

o Geyer For point process models with the 'Geyer' interaction, vcov.ppm() and suffstat() sometimes gave incorrect answers. [Spotted by Ege Rubak.] Fixed.

o as.im.im Did not correctly handle factor-valued images if one of the arguments 'dimyx', 'eps', 'xy' was given. Fixed.

o envelope.lppm Crashed if the model was multitype. Fixed.

o lpp Did not handle empty patterns. Fixed.

o density.ppp If 'sigma' was a bandwidth selection function such as bw.scott() which returned a numeric vector of length 2, a warning message was issued, and the smoothing bandwidth was erroneously taken to be the first element of the vector. Fixed.

o Fest, Jcross, Jdot, Jmulti
If these functions were computed using correction = 'rs',
plotting them would sometimes give an error,

with the message "no finite x/y limits".
Fixed.

o pcfmodel.kppm For models with clusters="VarGamma" the value of the pcf at distance r=0 was given as NaN. Fixed.

o vcov.ppm Result was incorrect in rare cases, due to numerical rounding effects. Fixed.

o rLGCP, simulate.kppm For models fitted to point patterns in an irregular window, simulation sometimes failed, with a message that the image 'mu' did not cover the simulation window. (Spotted by George Limitsios.) Fixed.

o rLGCP, simulate.kppm Crashed sometimes with an error about unequal x and y steps (from 'GaussRF'). Fixed.

```
CHANGES IN spatstat VERSION 1.29-0
```

OVERVIEW

o We thank Colin Beale, Li Haitao, Frederic Lavancier, Erika Mudrak and Ege Rubak for contributions.

o random sequential packing

o Allard-Fraley estimator

o method for pooling several quadrat tests

o better control over dummy points in ppm

o more support for data on a linear network

o nearest neighbour map

o changes to subsetting of images

o improvements and bug fixes

NEW FUNCTIONS

o clusterset Allard-Fraley estimator of high-density features in a point pattern

o pool.quadrattest Pool several quadrat tests

o nnfun Nearest-neighbour map of a point pattern or a line segment pattern

o as.ppm Converts various kinds of objects to ppm

o crossdist.lpp Shortest-path distances between pairs of points in a linear network

o nobs.lppm Method for 'nobs' for lppm objects.

o as.linim Converts various kinds of objects to 'linim'

o model.images.slrm Method for model.images for slrm objects

o rotate.im Rotate a pixel image

SIGNIFICANT USER-VISIBLE CHANGES

o "[.im" and "[<-.im" New argument 'j' allows any type of matrix indexing to be used.

o "[.im" Default behaviour changed in the case of a rectangular subset. New argument 'rescue' can be set to TRUE to reinstate previous behaviour.

o rSSI Performs 'Random Sequential Packing' if n=Inf.

o ppm New argument 'eps' determines the spacing between dummy points. (also works for related functions quadscheme, default.dummy, ...)

o fitted.ppm, predict.ppm Argument 'new.coef' specifies a vector of parameter values to replace the fitted coefficients of the model.

o lppm Stepwise model selection using step() now works for lppm objects.

o vcov.slrm Can now calculate correlation matrix or Fisher information matrix as well as variance-covariance matrix.

o eval.fv Improved behaviour when plotted.

o "[.fv" Improved behaviour when plotted.

o lohboot When the result is plotted, the confidence limits are now shaded.

o lohboot New argument 'global' allows global (simultaneous) confidence bands instead of pointwise confidence intervals.

o vcov.ppm Accelerated by 30% in some cases.

o quadrat.test.splitppp The result is now a single object of class 'quadrattest'

o progressreport Improved output (also affects many functions which print progress reports)

o Full redwood data (redwoodfull) Plot function redwoodfull.extra$plotit has been slightly improved.

o nncross This function is now generic, with methods for 'ppp' and 'default'.

o distfun The internal format of objects of class 'distfun' has been changed.

o duplicated.ppp, unique.ppp

New argument 'rule' allows behaviour to be consistent with package 'deldir'

BUG FIXES

o bdist.tiles Values were incorrect in some cases due to numerical error. (Spotted by Erika Mudrak.) Fixed.

o vcov.ppm, suffstat These functions sometimes gave incorrect values for marked point process models. Fixed.

o simulate.ppm, predict.ppm Did not correctly handle the 'window' argument. (Spotted by Li Haitao). Fixed.

o smooth.ppp, markmean If sigma was very small, strange values were produced, due to numerical underflow. (Spotted by Colin Beale). Fixed.

o MultiHard, MultiStrauss, MultiStraussHard Crashed if the data point pattern was empty. (Spotted by Ege Rubak). Fixed.

o vcov.ppm Crashed sporadically, with multitype interactions. (Spotted by Ege Rubak). Fixed.

o rStrauss, rHardcore, rStraussHard, rDiggleGratton, rDGS If the simulated pattern was empty, these functions would either crash, or return a pattern containing 1 point. (Spotted by Frederic Lavancier). Fixed.

o model.matrix.slrm Crashed if the model was fitted using split pixels. Fixed.

o residuals.ppm, diagnose.ppm Did not always correctly handle models that included offset terms. Fixed.

o project.ppm When a model was projected by project.ppm or by ppm(project=TRUE), the edge corrections used the projected models were sometimes different from the edge corrections in the original model, so that the projected and unprojected models were not comparable. Fixed.

o plot.listof, plot.splitppp Crashed sometimes due to a scoping problem. Fixed.

o dclf.test, mad.test Crashed if any of the function values were infinite or NaN. Fixed.

o psstA Default plot did not show the horizontal line at y=0 corresponding to a perfect fit. Fixed.

o vcov.ppm names attribute was spelt incorrectly in some cases. Fixed.

```
CHANGES IN spatstat VERSION 1.28-2
```

OVERVIEW

o We thank Thomas Bendtsen, Ya-Mei Chang, Daniel Esser, Robert John-Chandran, Ege Rubak and Yong Song for contributions.

o New code for Partial Residual Plots and Added Variable Plots.

o maximum profile pseudolikelihood computations vastly accelerated.

o New dataset: cells in gastric mucosa

o now possible to capture every k-th state of Metropolis-Hastings algorithm.

o size of 'ppm' objects reduced.

o scope of 'intensity.ppm' extended.

o quadrat.test can now perform Monte Carlo tests and one/two-sided tests

o improvements to 'plot.fv'

o improvement to 'rescale'

o some datasets reorganised.

o numerous bug fixes

NEW DATASET

o mucosa Cells in gastric mucosa Kindly contributed by Dr Thomas Bendtsen

NEW FUNCTIONS

o parres Partial residual plots for spatial point process models. A diagnostic for the form of a covariate effect.

o addvar Added variable plots for spatial point process models. A diagnostic for the existence of a covariate effect.

SIGNIFICANT USER-VISIBLE CHANGES

o profilepl Accelerated (typically by a factor of 5).

o rmh, rmhcontrol It is now possible to save every k-th iteration of the Metropolis-Hastings algorithm. The arguments 'nsave' and 'nburn' may be given to rmh or to rmhcontrol. They specify that the point pattern will be saved every 'nsave' iterations, after an initial burn-in of 'nburn' iterations.

o simulate.ppm New argument 'singlerun' determines whether the simulated patterns are generated using independent runs of the Metropolis-Hastings algorithm or are obtained by performing one long run of the algorithm and saving every k-th iteration.

o exactMPLEstrauss New argument 'project' determines whether the parameter gamma is constrained to lie in [0,1].

o intensity.ppm Now works for stationary point process models with the interactions DiggleGratton, DiggleGatesStibbard, Fiksel, PairPiece and Softcore.

o plot.fv Improved algorithm for avoiding collisions between graphics and legend.

o plot.fv New argument 'log' allows plotting on logarithmic axes.

o envelope Can now calculate an estimate of the true significance level of the "wrong" test (which declares the observed summary function to be significant if it lies outside the pointwise critical boundary anywhere). Controlled by new argument 'do.pwrong'.

o quadrat.test New argument 'alternative' allows choice of alternative hypothesis and returns one-sided or two-sided p-values as appropriate.

o quadrat.test Can now perform Monte Carlo test as well (for use in small samples where the chi^2 approximation is inaccurate)

o Softcore Improved numerical stability. New argument 'sigma0' for manual control over rescaling.

o rescale If scale argument 's' is missing, then the data are rescaled to native units. For example if the current unit is 0.1 metres, coordinates will be re-expressed in metres.

o psst Extra argument 'verbose=TRUE'

o is.subset.owin Accelerated for polygonal windows

o rmh.default 'track' is no longer a formal argument of rmh.default; it is now a parameter of rmhcontrol. However there is no change in usage: the argument 'track' can still be given to rmh.default.

o clf.test Has been renamed 'dclf.test' to give proper attribution to Peter Diggle.

o betacells This dataset has been restructured. The vector of cell profile areas, formerly given by betacells.extra$area, has now been included as a column of marks in the point pattern 'betacells'.

o ants The function ants.extra$plot() has been renamed plotit() for conformity with other datasets.

o redwoodfull The function redwoodfull.extra$plot() has been renamed plotit() for conformity with other datasets.

o nbfires For conformity with other datasets, there is now an object nbfires.extra

BUG FIXES

o ripras Expansion factor was incorrect in the rectangular case. Fixed.

o Triplets Crashed sometimes with error "dim(X) must have positive length". Fixed.

o affine.im Crashed in the case of a diagonal transformation matrix! Spotted by Ege Rubak. Fixed.

o envelope.envelope Ignored the argument 'global'. Fixed.

o MultiStraussHard The printed output showed the hardcore radii as NULL. Spotted by Ege Rubak. Fixed.

o "[.psp" Crashed if the data were generated by rpoisline(). Spotted by Marcelino de la Cruz. Fixed.

o plot.linim If style="colour", the main title was always "x". Fixed.

o plot.ppx Setting add=TRUE did not prevent the domain being plotted. Fixed.

o rmh Crashed if x.start was an empty point pattern. Spotted by Ege Rubak. Fixed.

o as.ppp.data.frame Crashed if any points lay outside the window. Spotted by Ege Rubak. Fixed.

o Ripley isotropic edge correction Divide-by-zero error in rare cases. Spotted by Daniel Esser. Fixed.

o summary functions For many of the summary functions (e.g. Kest, pcf), the result of saving the object to disc was an enormous file. Spotted by Robert John-Chandran. Fixed.

o pcf.fv Default plot was wrongly coloured. Fixed.

```
CHANGES IN spatstat VERSION 1.28-1
```

OVERVIEW

o We thank Ege Rubak, Gopal Nair, Jens Oehlschlaegel and Mike Zamboni for contributions.

o New approximation to the intensity of a fitted Gibbs model.

o Minor improvements and bug fixes

o spatstat now 'Suggests' the package 'gsl'

NEW FUNCTIONS

o intensity, intensity.ppp, intensity.ppm Calculate the intensity of a dataset or fitted model. Includes new approximation to the intensity of a fitted Gibbs model

o LambertW Lambert's W-function

SIGNIFICANT USER-VISIBLE CHANGES

o envelope Improved plot labels for envelopes that were generated using the 'transform' argument.

o plot.fv Improved algorithm for collision detection.

o plot.im Now returns the colour map used.

o plot.listof, plot.splitppp Slight change to handling of plot.begin and plot.end

o square Now accepts vectors of length 2

o plot.fii Increased resolution of the plot obtained from plot(fitin(ppm(...)))

o image.listof If equal.ribbon=TRUE, the colour ribbon will no longer be displayed repeatedly for each panel, but will now be plotted only once, at the right hand side of the plot array.

BUG FIXES

o vcov.ppm Results were sometimes incorrect for a Gibbs model with non-trivial trend. Spotted by Ege Rubak. Fixed.

o nncross In rare cases the results could be slightly incorrect. Spotted by Jens Oehlschlaegel. Fixed.

o plot.fv When add=TRUE, the x limits were sometimes truncated. Spotted by Mike Zamboni. Fixed.

o plot.im Labels for the tick marks on the colour ribbon were sometimes ridiculous, e.g. "2.00000001". Fixed.

```
CHANGES IN spatstat VERSION 1.28-0
```

OVERVIEW

o We thank Farzaneh Safavimanesh, Andrew Hardegen and Tom Lawrence for contributions.

o Improvements to 3D summary functions.

o A multidimensional point pattern (ppx) can now have 'local' coordinates as well as spatial and temporal coordinates and marks.

o Changed format for point patterns on a linear network (lpp). Changes are backward compatible. Many computations run faster.

o More support for fitted cluster models (kppm).

o split method for multidimensional point patterns (ppx) and point patterns on a linear network (lpp).

o Fixed bug causing errors in plot.im

o Miscellaneous improvements and bug fixes

NEW FUNCTIONS

o exactMPLEstrauss Fits the stationary Strauss point process model using an exact maximum pseudolikelihood technique. This is mainly intended for technical investigation of algorithms.

o split.ppx Method for 'split' for multidimensional point patterns (class 'ppx'). This also works for point patterns on a linear network (class 'lpp').

o model.images This function is now generic, with methods for classes ppm, kppm, lppm

o model.frame, model.matrix These generic functions now have methods for classes kppm, lppm

o as.owin.kppm, as.owin.lppm New methods for 'as.owin' for objects of class kppm, lppm

o as.linnet.lppm Extracts the linear network in which a point process model was fitted.

SIGNIFICANT USER-VISIBLE CHANGES

o class 'ppx' An object of class 'ppx' may now include 'local' coordinates as well as 'spatial' and 'temporal' coordinates, and marks.

o ppx Arguments have changed.

o class 'lpp' The internal format of lpp objects has been extended (but is backward-compatible). Many computations run faster. To convert an object to the new format: X <- lpp(as.ppp(X), as.linnet(X)).

o F3est Calculation of theoretical Poisson curve ('theo') has changed, and is now controlled by the argument 'sphere'.

o rmh, rmhstart The initial state ('start') can now be missing or null.

o im, as.im The pixel coordinates in an image object are now generated more accurately. This avoids a numerical error in plot.im.

o eval.fv, eval.fasp Evaluation is now applied only to columns that contain values of the function itself (rather than values of the derivative, hazard rate, etc). This is controlled by the new argument 'dotonly'.

o spatstat.options New option 'nvoxel'

o quad.ppm Now accepts kppm objects.

o str This generic function (for inspecting the internal structure of an object) now produces sensible output for objects of class 'hyperframe', 'ppx', 'lpp'

o ppx, coords.ppx, coords<-.ppx The arguments to these functions have changed.

o lgcp.estK, Kmodel Computation can be greatly accelerated by setting spatstat.options(fastK.lgcp=TRUE).

o G3est Computation accelerated.

o envelope Computation slightly accelerated.

o spatstat.options New option 'fastK.lgcp'

BUG FIXES

o nndist.psp Caused an error if length(k) > 1. Fixed.

o plot.im Sometimes reported an error "useRaster=TRUE can only be used with a regular grid." This was due to numerical rounding effects on the coordinates of a pixel image. Fixed.

o plot.fv
If a formula was used to specify the plot,
the names of variables in the formula were sometimes
incorrectly matched to *functions*.
Spotted by Farzaneh Safavimanesh.
Fixed.

o F3est Took a very long time if the containing box was very flat, due to the default value of 'vside'. Fixed.

o rmh, rmhmodel An erroneous warning about 'outdated format of rmhmodel object' sometimes occurred. Fixed.

o marks<-.ppx Names of result were incorrect. Fixed.

o hyperframe class Various minor bug fixes.

```
CHANGES IN spatstat VERSION 1.27-0
```

OVERVIEW

o Variance estimates are now available for all Gibbs point process models.

o Cressie-Loosmore-Ford test implemented

o plot.fv now avoids collisions between the legend and the graphics.

o Extension to predict.ppm

o Improvements to envelopes and multitype summary functions.

o Line transects of a pixel image.

o Changes to defaults in Metropolis-Hastings simulations.

o More geometrical operations

o Bug fixes.

o We thank Aruna Jammalamadaka for contributions.

NEW FUNCTIONS

o clf.test Perform the Cressie (1991)/ Loosmore and Ford (2006) test of CSR (or another model)

o mad.test Perform the Maximum Absolute Deviation test of CSR (or another model).

o convolve.im Compute convolution of pixel images.

o Kmulti.inhom Counterpart of 'Kmulti' for spatially-varying intensity.

o rmhexpand Specify a simulation window, or a rule for expanding the simulation window, in Metropolis-Hastings simulation (rmh)

o transect.im Extract pixel values along a line transect.

o affine.im Apply an affine transformation to a pixel image.

o scalardilate Perform scalar dilation of a geometrical object relative to a specified origin.

o reflect Reflect a geometrical object through the origin.

o "[.lpp", "[.ppx" Subset operators for the classes "lpp" (point pattern on linear network) and "ppx" (multidimensional space-time point pattern).

o is.rectangle, is.polygonal, is.mask Determine whether a window w is a rectangle, a domain with polygonal boundaries, or a binary pixel mask.

o has.offset Determines whether a fitted model object (of any kind) has an offset.

SIGNIFICANT USER-VISIBLE CHANGES

o predict.ppm This function can now calculate the conditional intensity of a model relative to any point pattern X (not just the original data pattern).

o vcov.ppm This function now handles all Gibbs point process models.

o plot.fv Collisions between the legend box and the graphics are now detected and avoided.

o rmh.ppm, rmh.default, simulate.ppm, qqplot.ppm, envelope.ppm These functions now have slightly different default behaviour because of changes to the handling of arguments to 'rmhcontrol'.

o rmhcontrol The default value of the parameters 'periodic' and 'expand' has changed.

o rmhcontrol The parameter 'expand' can now be in any format acceptable to rmhexpand().

o rmh.ppm, rmh.default, simulate.ppm Any 'rmhcontrol' parameter can now be given directly as an argument to rmh.ppm, rmh.default or simulate.ppm.

o Kmulti, Gmulti, Jmulti The arguments I, J can now be any kind of subset index or can be functions that yield a subset index.

o envelope.envelope In envelope(E, fun=NULL) if E does not contain simulated summary functions, but does contain simulated point patterns, then 'fun' now defaults to Kest, instead of flagging an error.

o print.ppp, summary.ppp If the point pattern x was generated by Metropolis-Hastings simulation using 'rmh', then print(x) and summary(x) show information about the simulation parameters.

o print.ppm Standard errors for the parameter estimates, and confidence intervals for the parameters, can now be printed for all Gibbs models (but are printed only for Poisson models by default).

o eval.im Images with incompatible dimensions are now resampled to make them compatible (if harmonize=TRUE).

o spatstat.options New option 'print.ppm.SE' controls whether standard errors and confidence intervals are printed for all Gibbs models, for Poisson models only, or are never printed.

o inside.owin Now accepts the form list(x,y) for the first argument.

o image.listof New argument 'equal.ribbon' allows several images to be plotted with the same colour map.

o is.subset.owin Improved accuracy in marginal cases.

o expand.owin Functionality extended to handle all types of expansion rule.

o default.rmhcontrol, default.expand These functions now work with models of class 'rmhmodel' as well as 'ppm'

o print.rmhcontrol Output improved.

BUG FIXES

o linearK, linearKinhom If any data points were located exactly at a vertex of the linear network, the weights for Ang's correction were incorrect, due to numerical error. This sometimes produced infinite or NA values of the linear K function. Fixed.

o predict.ppm In some cases, predict.ppm(type="cif") generated a spurious warning that "number of rows of result is not a multiple of vector length." Fixed.

o crossing.psp Results were sometimes incorrect due to numerical rounding error associated with GCC bug #323. Fixed.

o MultiHard, MultiStrauss, MultiStraussHard If the mark values contained non-alphanumeric characters, the names of the interaction coefficients in coef(ppm(...)) were sometimes garbled. Fixed.

o profilepl For edge corrections other than the border correction, an error message about 'rbord' would sometimes occur. Fixed.

o is.marked, is.multitype These functions gave the wrong answer for 'lpp' objects. Fixed.

o marks<-.lpp, marks<-.ppx Format of result was garbled if new columns of marks were added. Fixed.

o reach.rmhmodel Gave the wrong answer for Geyer and BadGey models. Fixed.

o envelope.envelope Ignored the argument 'savefuns'. Fixed.

o BadGey Sometimes wrongly asserted that the parameter 'sat' was invalid. Occurred only in ppm(project=TRUE). Fixed.

```
CHANGES IN spatstat VERSION 1.26-1
```

OVERVIEW

o Variance-covariance matrix for Gibbs point process models.

o Bootstrap confidence bands for pair correlation function and K function.

o Bug fix in scan test.

o Area-interaction model accelerated.

o we thank Jean-Francois Coeurjolly and Ege Rubak for contributions.

NEW FUNCTIONS

o lohboot Computes bootstrap confidence bands for pair correlation function and K function using Loh's (2008) mark bootstrap.

SIGNIFICANT USER-VISIBLE CHANGES

o vcov.ppm Now works for all Gibbs point process models, thanks to new code (and theory) from Jean-Francois Coeurjolly and Ege Rubak

o AreaInter Computations related to the area-interaction point process (ppm, predict.ppm, residuals.ppm, diagnose.ppm, qqplot.ppm) have been accelerated.

BUG FIXES

o scan.test Results were sometimes incorrect due to numerical instability (a 'Gibbs phenomenon'). Fixed.

```
CHANGES IN spatstat VERSION 1.26-0
```

OVERVIEW

o We thank Jens Oehlschlaegel for contributions.

o Further substantial acceleration of spatstat functions.

o Workaround for bug in RandomFields package.

o Numerous modifications to internal code.

NEW FUNCTIONS

o RandomFieldsSafe There is a bug in the package 'RandomFields' (version <= 2.0.54) which causes a crash to occur, in the development version of R but not in R 2.15.0. To avoid crashing spatstat, we have written the temporary, undocumented function RandomFieldsSafe() which returns TRUE if it is safe to use the RandomFields package. Examples in the spatstat help files for kppm, lgcp.estK, lgcp.estpcf and rLGCP are only executed if RandomFieldsSafe() returns TRUE.

SIGNIFICANT USER-VISIBLE CHANGES

o Many functions Many spatstat functions now run faster, and will handle larger datasets, thanks to improvements in the internal code, following suggestions from Jens Oehlschlaegel.

o Many functions The response to an 'Interrupt' signal is slightly slower.

```
CHANGES IN spatstat VERSION 1.25-5
```

OVERVIEW

o We thank Ya-Mei Chang, Jens Oehlschlaegel and Yong Song for contributions.

o Extended functionality of 'rhohat' to local likelihood smoothing and bivariate smoothing.

o Nearest neighbour distance computations accelerated.

o spatstat now 'Suggests:' the package 'locfit'

NEW FUNCTIONS

o rho2hat Bivariate extension of 'rhohat' for estimating spatial residual risk, or intensity as a function of two covariates.

SIGNIFICANT USER-VISIBLE CHANGES

o rhohat Estimation can now be performed using local likelihood fitting with the 'locfit' package, or using kernel smoothing.

o nncross Substantially accelerated. New arguments added to control the return value and the sorting of data.

BUG FIXES

o plot.msr Crashed if the argument 'box' was given. Fixed.

```
CHANGES IN spatstat VERSION 1.25-4
```

OVERVIEW

o We thank Jonathan Lee and Sergiy Protsiv for contributions.

o Improvements and bug fixes to K function for very large datasets

NEW FUNCTIONS

o rStraussHard Perfect simulation for Strauss-hardcore process (with gamma <= 1)

SIGNIFICANT USER-VISIBLE CHANGES

o plot.im The colour ribbon can now be placed left, right, top or bottom using new argument 'ribside'

o profilepl Does not generate warnings when some of the candidate models have zero likelihood - for example when fitting model with a hard core.

o Kest Now includes fast algorithm for 'correction="none"' which will handle patterns containing millions of points.

BUG FIXES

o Kest, Lest Gave incorrect values in very large datasets, due to numerical overflow. `Very large' typically means about 1 million points in a random pattern, or 100,000 points in a tightly clustered pattern. [Overflow cannot occur unless there are at least 46,341 points.] [Spotted by Sergiy Protsiv.] Fixed.

o Kest, Lest Ignored 'ratio=TRUE' if the argument 'domain' was given. [Spotted by Jonathan Lee.] Fixed.

o rjitter Output was sometimes incorrect. [Spotted by Sergiy Protsiv.] Fixed.

```
CHANGES IN spatstat VERSION 1.25-3
```

OVERVIEW

o We thank Daniel Esser for contributions.

o Improved support for fitted point process models.

o Bug fixes.

NEW FUNCTIONS

o simulate.slrm Method for 'simulate' for spatial logistic regression models.

o labels.ppm, labels.kppm, labels.slrm Methods for 'labels' for fitted point process models.

o commonGrid Determine a common spatial domain and pixel resolution for several pixel images and/or binary masks

SIGNIFICANT USER-VISIBLE CHANGES

o effectfun Now has argument 'se.fit' allowing calculation of standard errors and confidence intervals.

o [.msr Now handles character-valued indices.

o print.summary.ppm Output gives a more precise description of the fitting method.

o ppm, kppm, slrm Confidence intervals for the fitted trend parameters can now be obtained using 'confint'

o predict.slrm New argument 'window'

o union.owin Now handles a single argument: union.owin(A) returns A.

BUG FIXES

o selfcrossing.psp y coordinate values were incorrect. [Spotted by Daniel Esser.] Fixed.

o as.im.owin Did not handle a binary mask with a 1 x 1 pixel array. Fixed.

o predict.slrm Results of predict(object, newdata) were incorrect if the spatial domain of 'newdata' was larger than the original domain. Fixed.

o ppm If the model was the uniform Poisson process, the argument 'rbord' was ignored. Fixed.

o image subset assignment "[<-.im" Generated an error if the indexing argument 'i' was a point pattern containing zero points. Fixed.

o hyperframe subset assignment "[<-.hyperframe" Did not correctly handle the case where a single column of the hyperframe was to be changed. Fixed.

o help(bw.relrisk), help(rmh.ppm), help(plot.plotppm) These help files had the side-effect of changing some options in spatstat.options. Fixed.

```
CHANGES IN spatstat VERSION 1.25-2
```

OVERVIEW

o We thank Abdollah Jalilian and Thierry Onkelinx for contributions.

o Very Important Bug fixes.

o Improved mechanism for handling 'invalid' point processes

NEW FUNCTIONS

o as.matrix.owin Converts a window to a logical matrix.

SIGNIFICANT USER-VISIBLE CHANGES

o project.ppm Improved algorithm. Now handles terms in the trend formula as well as the interaction. The projected point process is now obtained by re-fitting the model, and is guaranteed to be the maximum pseudolikelihood fit.

o plot.im Now handles many arguments recognised by plot.default such as 'cex.main'. Also handles argument 'box'. New argument 'ribargs' contains parameters controlling the ribbon plot only.

o spatstat.options New option 'project.fast' allows a faster shortcut for project.ppm

o spatstat.options New options 'rmh.p', 'rmh.q', 'rmh.nrep' determine the default values of the parameters p, q and nrep of the Metropolis-Hastings algorithm. See rmhcontrol

o ppm Slightly accelerated.

BUG FIXES

o nncross, distfun, AreaInter Results of nncross were possibly incorrect when X and Y did not have the same window. This bug affected values of 'distfun' and may also have affected ppm objects with interaction 'AreaInter'. [Spotted by Thierry Onkelinx] Bug introduced in spatstat 1.9-4 (June 2006). Fixed.

o rCauchy Simulations were incorrect in the sense that the value of 'omega' was inadvertently doubled (i.e. omega was incorrectly replaced by 2 * omega). Bug introduced in spatstat 1.25-0. Fixed.

o plot.im White lines were present in the image display, on some graphics devices, due to changes in R 2.14. Fixed.

o update.ppm The result of 'update(object, formula)' sometimes contained errors in the internal format. Bug introduced in spatstat 1.25-0. Fixed.

o example(AreaInter), example(bw.smoothppp), example(Kest.fft), example(plot.owin), example(predict.ppm), example(simulate.ppm) Executing these examples had the side-effect of changing some of the parameters in spatstat.options. Fixed.

```
CHANGES IN spatstat VERSION 1.25-1
```

OVERVIEW

o We thank Neba Funwi-Gabga and Jorge Mateu for contributions.

o New dataset of gorilla nest sites

o New functions for perfect simulation

o Bug fix for rare crashes in rStrauss

o Code for ensuring a fitted point process model is a valid point process

NEW DATASET

o gorillas Gorilla nest sites in a National Park in Cameroon. Generously contributed by Neba Funwi-Gabga

NEW FUNCTIONS

o rDiggleGratton, rDGS, rHardcore Perfect simulation for the Diggle-Gratton process, Diggle-Gates-Stibbard process, and Hardcore process.

o bw.scott Scott's rule of thumb for bandwidth selection in multidimensional smoothing

o valid.ppm Checks whether a fitted point process model is a valid point process

o project.ppm Forces a fitted point process model to be a valid point process

SIGNIFICANT USER-VISIBLE CHANGES

o ppm New argument 'project' determines whether the fitted model is forced to be a valid point process

o linnet Substantially accelerated.

o rStrauss Slightly accelerated.

o summary.lpp Now prints the units of length.

BUG FIXES

o rStrauss Crashed rarely (once every 10 000 realisations) with a memory segmentation fault. Fixed.

```
CHANGES IN spatstat VERSION 1.25-0
```

OVERVIEW

o Leverage and influence for point process models

o New cluster models (support for model-fitting and simulation).

o Fit irregular parameters in trend of point process model

o Third order summary statistic.

o Improvements to speed and robustness of code.

o spatstat now depends on R 2.14

o We thank Abdollah Jalilian and Rasmus Waagepetersen for contributions.

NEW FUNCTIONS

o leverage.ppm, influence.ppm, dfbetas.ppm Leverage and influence for point process models

o ippm Experimental extension to 'ppm' which fits irregular parameters in trend by Fisher scoring algorithm.

o Tstat Third order summary statistic for point patterns based on counting triangles.

o rCauchy, rVarGamma simulation of a Neyman-Scott process with Cauchy clusters or Variance Gamma (Bessel) clusters. Contributed by Abdollah Jalilian.

o rPoissonCluster simulation of a general Poisson cluster process

o model.covariates Identify the covariates involved in a model (lm, glm, ppm etc)

o as.im.distfun Converts a 'distfun' to a pixel image.

o cauchy.estK, cauchy.estpcf, vargamma.estK, vargamma.estpcf Low-level model-fitting functions for the Neyman-Scott process with Cauchy or Variance-Gamma cluster kernel. Contributed by Abdollah Jalilian.

SIGNIFICANT USER-VISIBLE CHANGES

o kppm Now accepts clusters="Cauchy" or clusters="VarGamma" for the Neyman-Scott process with Cauchy or Variance-Gamma cluster kernel. Code contributed by Abdollah Jalilian.

o rNeymanScott Argument 'rcluster' may now take a different format.

o psst Argument 'funcorrection' changed to 'funargs' allowing greater flexibility.

o plot.fv, plot.envelope New argument 'limitsonly' allows calculation of a common x,y scale for several plots.

o overall speed spatstat is now byte-compiled and runs slightly faster.

o user interrupt Long calculations in spatstat now respond to the Interrupt/Stop signal.

o update.ppm Now runs faster and uses much less memory, when the update only affects the model formula (trend formula).

o rNeymanScott, rThomas, rMatClust Accelerated thanks to Rasmus Waagepetersen.

o multitype data and models Second order multitype statistics (such as Kcross, pcfcross) and multitype interaction models (such as MultiStrauss) now run faster, by a further 5%.

BUG FIXES

o distfun Some manipulations involving 'distfun' objects failed if the original data X in distfun(X) did not have a rectangular window. Fixed.

```
CHANGES IN spatstat VERSION 1.24-2
```

OVERVIEW

o Geyer's triplet interaction

o more functionality for replicated point patterns

o changed default for simulation window in point process simulation

o changed default for edge correction in Kcom, Gcom

o data in spatstat is now lazy-loaded

o bug fixes

NEW FUNCTIONS

o Triplets Geyer's triplet interaction, for point process models

o coef.summary.ppm New method coef.summary.ppm You can now type 'coef(summary(fit))' to extract a table of the fitted coefficients of the point process model 'fit'

SIGNIFICANT USER-VISIBLE CHANGES

o data in spatstat are now lazy-loaded so you don't have to type data(amacrine), etc.

o rmh.default, rmh.ppm, simulate.ppm These now handle the 'triplets' interaction

o fryplot Now has arguments 'to' and 'from', allowing selection of a subset of points.

o fryplot, frypoints These functions now handle marked point patterns properly.

o Kcross, Kdot, Kmulti New argument 'ratio' determines whether the numerator and denominator of the estimate of the multitype K-function will be stored. This enables analysis of replicated point patterns, using 'pool.rat()' to pool the K function estimates.

o rmh.ppm, simulate.ppm, default.expand For point process models which have a trend depending only on x and y, the simulation window is now taken to be the same as the original window containing the data (by default). That is, `expansion' does not take place, by default. (In previous versions of spatstat the simulation window was larger than the original data window.)

o rmh.ppm, simulate.ppm The argument sequence for these functions has changed. New argument 'expand' allows more explicit control over simulation domain.

o Kcom, Gcom New argument 'conditional' gives more explicit control over choice of edge correction in compensator. Simplified defaults for edge correction.

o Kinhom Improved plot labels.

o profilepl Printed output improved.

BUG FIXES

o Lest The variance approximations (Lotwick-Silverman and Ripley) obtained with var.approx=TRUE, were incorrect for Lest (although they were correct for Kest) due to a coding error. Fixed.

o simulate.ppm Ignored the argument 'control' in some cases. Fixed.

o pcf and its relatives (pcfinhom, pcfcross.inhom, pcfdot.inhom) Sometimes gave a warning about 'extra arguments ignored'. Fixed.

```
CHANGES IN spatstat VERSION 1.24-1
```

OVERVIEW

o Spatial Scan Test

o Functionality for replicated point patterns

o Bug fixes

NEW FUNCTIONS

o scan.test Spatial scan test of clustering

o rat New class of 'ratio objects'

o pool.rat New method for 'pool'. Combines K function estimates for replicated point patterns (etc) by computing ratio-of-sums

o unnormdensity Weighted kernel density with weights that do not sum to 1 and may be negative.

o compatible New generic function with methods for 'fv', 'im', 'fasp' and 'units'

SIGNIFICANT USER-VISIBLE CHANGES

o Kest New argument 'ratio' determines whether the numerator and denominator of the estimate of the K-function will be stored. This enables analysis of replicated point patterns, using 'pool.rat()' to pool the K function estimates.

o Lest Now handles theoretical variance estimates (using delta method) if var.approx=TRUE

o as.mask Argument 'eps' can now be a 2-vector, specifying x and y resolutions.

o default.expand Behaviour changed slightly.

o plot.listof, plot.splitppp, contour.listof, image.listof The arguments 'panel.begin' and 'panel.end' can now be objects such as windows.

BUG FIXES

o rgbim, hsvim Did not work on images with non-rectangular domains. Fixed.

o scaletointerval Did not handle NA's. Fixed.

```
CHANGES IN spatstat VERSION 1.24-0
```

OVERVIEW

o This version was not released publicly.

```
CHANGES IN spatstat VERSION 1.23-6
```

OVERVIEW

o Spatial covariance functions of windows and pixel images.

o Area-interaction models can now be fitted in non-rectangular windows

o Bug fix for envelope of inhomogeneous Poisson process

o Bug fix for raster conversion

o New vignette on 'Getting Started with Spatstat'

o Code accelerated.

NEW FUNCTIONS

o imcov Spatial covariance function of pixel image or spatial cross-covariance function of two pixel images

o harmonise.im Make several pixel images compatible by converting them to the same pixel grid

o contour.listof, image.listof Methods for contour() and image() for lists of objects

o dummify Convert data to numeric values by constructing dummy variables.

SIGNIFICANT USER-VISIBLE CHANGES

o setcov Can now compute the `cross-covariance' between two regions

o AreaInter Point process models with the AreaInter() interaction can now be fitted to point pattern data X in any window.

o areaGain, areaLoss These now handle arbitrary windows W. They are now more accurate when r is very small.

o Kcom Computation vastly accelerated, for non-rectangular windows.

o vignettes New vignette 'Getting Started with the Spatstat Package'

o nncorr, nnmean, nnvario These functions now handle data frames of marks.

BUG FIXES

o envelope.ppm If the model was an inhomogeneous Poisson process, the resulting envelope object was incorrect (the simulations were correct, but the envelopes were calculated assuming the model was CSR). Bug was introduced in spatstat 1.23-5. Fixed.

o envelope.ppm If the model was an inhomogeneous Poisson process with intensity a function of x and y only, overflow errors sometimes occurred ('insufficient storage' or 'attempting to generate a large number of random points'). Fixed.

o as.im.im The result of as.im(X, W) was incorrect if 'W' did not cover 'X'. Fixed.

o as.mask The result of as.mask(w, xy) was incorrect if 'xy' did not cover 'w'. Fixed.

o plot.fv Legend was incorrectly labelled if 'shade' variables were not included in the plot formula. Fixed.

o areaGain, areaLoss Crashed if the radius r was close to zero. Fixed.

```
CHANGES IN spatstat VERSION 1.23-5
```

OVERVIEW

o Bug fix to bandwidth selection.

o Functions to pool data from several objects of the same class.

o Improvements and bug fixes.

o We thank Michael Sumner for contributions.

NEW FUNCTIONS

o pool Pool data from several objects of the same class

o pool.envelope Pool simulated data from several envelope objects and create a new envelope

o pool.fasp Pool simulated data from several function arrays and create a new array

o envelope.envelope Recalculate an envelope from simulated data using different parameters

SIGNIFICANT USER-VISIBLE CHANGES

o bw.diggle, bw.relrisk, bw.smoothppp, bw.optim Plot method modified.

o model.depends Now also recognises 'offset' terms.

BUG FIXES

o bw.diggle Bandwidth was too large by a factor of 2. Fixed.

o plot.psp Crashed if any marks were NA. Fixed.

o pointsOnLines Crashed if any segments had zero length. Ignored argument 'np' in some cases. Fixed.

o stieltjes Crashed if M had only a single column of function values. Fixed.

```
CHANGES IN spatstat VERSION 1.23-4
```

OVERVIEW

```
o Bandwidth selection for density.ppp and smooth.ppp
o Layered plots.
o Model-handling facilities.
o Improvements and bug fixes.
```

NEW FUNCTIONS

o bw.diggle Bandwidth selection for density.ppp by mean square error cross-validation.

o bw.smoothppp Bandwidth selection for smooth.ppp by least-squares cross-validation.

o layered, plot.layered A simple mechanism for controlling plots that consist of several successive layers of data.

o model.depends Given a fitted model (of any kind), identify which of the covariates is involved in each term of the model.

o model.is.additive Determine whether a fitted model (of any kind) is additive, in the sense that each term in the model involves at most one covariate.

SIGNIFICANT USER-VISIBLE CHANGES

o smooth.ppp Bandwidth 'sigma' is now selected by least-squares cross-validation

o bw.relrisk Computation in large datasets accelerated. New arguments 'hmin', 'hmax' control the range of trial values of bandwidth.

o Hest, Gfox, Jfox Improved algebraic labels for plot

o spatstat.options New parameter 'n.bandwidth'

o density.ppp, smooth.ppp Slightly accelerated.

o point-in-polygon test Accelerated.

BUG FIXES

```
o with.fv
Mathematical labels were incorrect in some cases.
Fixed.
o bw.relrisk
Implementation of method="weightedleastsquares" was incorrect
and was equivalent to method="leastsquares".
Fixed.
o smooth.ppp
NaN values occurred if the bandwidth was very small.
Fixed.
CHANGES IN spatstat VERSION 1.23-3
```

OVERVIEW

```
o Urgent bug fix.
```

BUG FIXES

```
o crossing.psp
Crashed occasionally with a message about NA or NaN values.
Fixed.
o affine.ppp
Crashed if the point pattern was empty.
Fixed.
CHANGES IN spatstat VERSION 1.23-2
```

OVERVIEW

```
o Bug fixes.
o Several functions have been accelerated.
o We thank Marcelino de la Cruz and Ben Madin for contributions.
```

NEW FUNCTIONS

```
o sumouter, quadform
Evaluate certain quadratic forms.
o flipxy
Exchange x and y coordinates.
```

SIGNIFICANT USER-VISIBLE CHANGES

o vcov.ppm Accelerated.

o owin, as.owin Checking the validity of polygons has been accelerated.

o crossing.psp, selfcrossing.psp Accelerated.

BUG FIXES

```
o split.ppp
If drop=TRUE then some of the point patterns had the wrong windows.
Spotted by Marcelino de la Cruz.
Fixed.
o split.ppp
Crashed if the tessellation did not cover the point pattern.
Fixed.
o predict.ppm
Crashed when type="se" if NA's were present.
Spotted by Ben Madin.
Fixed.
o plot.ppp
Incorrectly handled the case where both 'col' and 'cols' were present.
Fixed.
o polygon geometry
The point-in-polygon test gave the wrong answer in some boundary cases.
Fixed.
CHANGES IN spatstat VERSION 1.23-1
```

OVERVIEW

```
o Important bug fix to 'localpcf'.
o Inverse-distance weighted smoothing.
o Inhomogeneous versions of neighbourhood density functions.
o Internal repairs and bug fixes.
o We thank Mike Kuhn and Ben Madin for contributions.
```

NEW FUNCTIONS

```
o idw
Inverse-distance weighted smoothing.
o localKinhom, localLinhom, localpcfinhom
Inhomogeneous versions of localK, localL, localpcf
```

BUG FIXES

```
o localpcf
The columns of the result were in the wrong order.
[i.e. pair correlation functions were associated with the wrong points.]
Fixed.
o delaunay
If the union of several Delaunay triangles formed a triangle,
this was erroneously included in the result of delaunay().
Fixed.
o predict.ppm, plot.ppm
Sometimes crashed with a warning about 'subscript out of bounds'.
Fixed.
o point-in-polygon test
Vertices of a polygon were sometimes incorrectly classified
as lying outside the polygon.
Fixed.
o Internal code
Numerous tweaks and repairs to satisfy the package checker
for the future R version 2.14.
CHANGES IN spatstat VERSION 1.23-0
```

OVERVIEW

```
o point patterns on a linear network:
new tools including geometrically-corrected linear K function,
pair correlation function, point process models, envelopes
o changes to renormalisation of estimates in Kinhom and pcfinhom
o new dataset: Chicago street crime
o spatstat now 'Suggests:' the package RandomFields
o spatstat now has a Namespace
o we thank Mike Kuhn, Monia Mahling, Brian Ripley for contributions.
```

NEW DATASET

```
o chicago
Street crimes in the University district of Chicago.
A point pattern on a linear network.
```

NEW FUNCTIONS

```
o envelope.lpp
Simulation envelopes for point patterns on a linear network
o lineardisc
Compute the 'disc' of radius r in a linear network
o linearpcf
Pair correlation for point pattern on a linear network
o linearKinhom, linearpcfinhom
Inhomogeneous versions of the K function and pair correlation function
for point patterns on a linear network
o lppm
Fit point process models on a linear network.
o anova.lppm
Analysis of deviance for point process models on a linear network.
o predict.lppm
Prediction for point process models on a linear network.
o envelope.lppm
Simulation envelopes for point process models on a linear network.
o linim
Pixel image on a linear network
o plot.linim
Plot a pixel image on a linear network
```

SIGNIFICANT USER-VISIBLE CHANGES

o linearK New argument 'correction'. Geometrically-corrected estimation is performed by default (based on forthcoming paper by Ang, Baddeley and Nair)

o Kinhom New argument 'normpower' allows different types of renormalisation.

o pcfinhom Now performs renormalisation of estimate. Default behaviour changed - estimates are now renormalised by default.

BUG FIXES

```
o density.ppp
Crashed if argument 'varcov' was given.
Fixed.
CHANGES IN spatstat VERSION 1.22-4
```

OVERVIEW

```
o new diagnostics based on score residuals
o new dataset
o improvements to plotting summary functions
o We thank Ege Rubak, Jesper Moller, George Leser, Robert Lamb
and Ulf Mehlig for contributions.
```

NEW FUNCTIONS

```
o Gcom, Gres, Kcom, Kres
New diagnostics for fitted Gibbs or Poisson point process models
based on score residuals.
Gcom is the compensator of the G function
Gres is the residual of the G function
Kcom is the compensator of the K function
Kres is the residual of the K function
o psst, psstA, psstG
New diagnostics for fitted Gibbs or Poisson point process models
based on pseudoscore residuals.
psst is the pseudoscore diagnostic for a general alternative
psstA is the pseudoscore diagnostic for an Area-interaction alternative
psstG is the pseudoscore diagnostic for a Geyer saturation alternative
o compareFit
Computes and compares several point process models
fitted to the same dataset, using a chosen diagnostic.
o as.interact
Extracts the interpoint interaction structure (without parameters)
from a fitted point process model or similar object.
```

NEW DATASET

```
o flu
Spatial point patterns giving the locations of
influenza virus proteins on cell membranes.
Kindly released by Dr George Leser and Dr Robert Lamb.
```

SIGNIFICANT USER-VISIBLE CHANGES

o pixel images and grids The default size of a pixel grid, given by spatstat.options("npixel"), has been changed from 100 to 128. A power of 2 gives faster and more accurate results in many cases.

o residuals.ppm New arguments 'coefs' and 'quad' for advanced use (make it possible to compute residuals from a modified version of the fitted model.)

o relrisk New argument 'casecontrol' determines whether a bivariate point pattern should be treated as case-control data.

o plot.fv Further improvements in mathematical labels.

o plot.fv The formula can now include the symbols .x and .y as abbreviation for the function argument and the recommended function value, respectively.

o plot.fv New argument 'add'

BUG FIXES

o multitype summary functions (Kcross, Kdot, Gcross, Gdot, .....) Plotting these functions generated an error if the name of one of the types of points contained spaces, e.g. "Escherichia coli". Fixed.

```
CHANGES IN spatstat VERSION 1.22-3
```

OVERVIEW

```
o Important bug fix to simulation code
o Miscellaneous improvements
o spatstat now depends on R 2.13.0 or later
o We thank Ege Rubak, Kaspar Stucki, Vadim Shcherbakov,
Jesper Moller and Ben Taylor for contributions.
```

NEW FUNCTIONS

```
o is.stationary, is.poisson
New generic functions for testing whether a point process model
is stationary and/or Poisson.
Methods for ppm, kppm, slrm etc
o raster.xy
raster coordinates of a pixel mask
o zapsmall.im
'zapsmall' for pixel images
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o density.ppp
New argument 'diggle' allows choice of edge correction
o rotate.owin, affine.owin
These functions now handle binary pixel masks.
New argument 'rescue' determines whether rectangles will be preserved
```

BUG FIXES

```
o rmh, simulate.ppm
Serious bug - simulation was completely incorrect in the case of
a multitype point process with an interaction that does not depend
on the marks, such as ppm(betacells, ~marks, Strauss(60))
The calling parameters were garbled.
Fixed.
o effectfun
Crashed if the covariate was a function(x,y).
Fixed.
o lurking
Gave erroneous error messages about 'damaged' models.
Fixed.
o envelope.ppm
Did not recognise when the fitted model was equivalent to CSR.
Fixed.
o plot.ppx
Crashed in some cases. Fixed.
CHANGES IN spatstat VERSION 1.22-2
```

OVERVIEW

```
o Fitting and simulation of log-Gaussian Cox processes
with any covariance function
o More support for 'kppm' and 'rhohat' objects
o K-function for point patterns on a linear network
o Metropolis-Hastings algorithm now saves its transition history
o Easier control of dummy points in ppm
o Convert an 'fv' object to an R function
o spatstat now depends on the package 'RandomFields'
o We thank Abdollah Jalilian, Shen Guochun, Rasmus Waagepetersen,
Ege Rubak and Ang Qi Wei for contributions.
```

NEW FUNCTIONS

```
o linearK
Computes the Okabe-Yamada network K-function
for a point pattern on a linear network.
o pairdist.lpp
Shortest-path distances between each pair of points
on a linear network.
o vcov.kppm
Asymptotic variance-covariance matrix for regression parameters
in kppm object.
[Contributed by Abdollah Jalilian and Rasmus Waagepetersen]
o rLGCP
Simulation of log-Gaussian Cox processes
[Contributed by Abdollah Jalilian and Rasmus Waagepetersen]
o predict.rhohat
Method for 'predict' for objects of class 'rhohat'
Computes a pixel image of the predicted intensity.
o Kmodel, pcfmodel
Generic functions that compute the K-function or pair correlation function
of a point process *model*.
So far the only methods are for the class 'kppm'.
o as.function.fv
Converts a function value table (class 'fv') to a function in R
o coef.kppm
Method for 'coef' for objects of class 'kppm'
o unitname, unitname<-
These generic functions now have methods for fitted model objects
(classes ppm, slrm, kppm, minconfit) and quadrature schemes (quad).
o nobs.ppm
Method for 'nobs' for class 'ppm'.
Returns the number of points in the original data.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o kppm
Can now fit a log-Gaussian Cox process
o simulate.kppm
Can now simulate a fitted log-Gaussian Cox process
o lgcp.estK, lgcp.estpcf
These functions previously fitted a log-Gaussian Cox process
with exponential covariance. They can now fit a log-Gaussian Cox process
with any covariance function implemented by the RandomFields package.
o rmh
If track=TRUE, the history of transitions of the Metropolis-Hastings
algorithm is saved and returned.
o ppm
New argument 'nd' controls the number of dummy points.
o as.fv
Now handles objects of class kppm or minconfit.
o rhohat
If covariate = "x" or "y", the resulting object has the same
'unitname' as the original point pattern data.
o rhohat
Now has arguments 'eps, 'dimyx' to control pixel resolution.
o MultiStrauss, MultiHard, MultiStraussHard
Default value of 'types' has been changed to NULL.
o data(ants)
The auxiliary data 'ants.extra' now includes a function called 'side'
determining whether a given location is in the scrub or field region.
Can be used as a covariate in ppm, kppm, slrm.
o print.ppm
Now has argument 'what' to allow only selected information to be printed.
```

BUG FIXES

```
o profilepl
Crashed in some cases involving multitype interactions.
Fixed.
o plot.splitppp
Behaved incorrectly if 'main' was an expression.
Fixed.
o effectfun
Crashed in trivial cases.
Fixed.
o kppm, thomas.estpcf, matclust.estpcf, lgcp.estpcf
Gave a spurious warning message.
Fixed.
o step
When applied to ppm objects this gave a spurious warning.
Fixed.
CHANGES IN spatstat VERSION 1.22-1
```

OVERVIEW

```
o marked line segment patterns can now be plotted
o multitype point process models are now 'self-starting'
o new functions to manipulate colour images
```

NEW FUNCTIONS

```
o rgbim, hsvim
Specify three colour channels.
These functions convert three pixel images with numeric values
into a single image whose pixel values are strings representing colours.
o scaletointerval
Generic utility function to rescale data (including spatial data)
to a specified interval
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o plot.im
Can now plot images whose pixel values are strings representing colours.
New argument 'valuesAreColours'
o plot.psp
Now handles marked line segment patterns
and plots the marks as colours.
o MultiHard, MultiStrauss, MultiStraussHard
The argument 'types' can now be omitted;
it will be inferred from the point pattern data.
o rhohat
Improved mathematical labels (when the result of rhohat is plotted)
o plot.fv
Minor improvements in graphics
```

BUG FIXES

```
o several minor bug fixes and improvements to satisfy R-devel
CHANGES IN spatstat VERSION 1.22-0
```

OVERVIEW

```
o support for point patterns on a linear network
o 'superimpose' is now generic
o improved mathematical labels when plotting functions
```

NEW CLASSES

```
o linnet
An object of class 'linnet' represents a linear network,
i.e. a connected network of line segments, such as a road network.
Methods for this class include plot, print, summary etc.
o lpp
An object of class 'lpp' represents a point pattern on a linear network,
such as a record of the locations of road accidents on a road network.
Methods for this class include plot, print, summary etc.
```

NEW FUNCTIONS

```
o runiflpp
Uniformly distributed random points on a linear network
o rpoislpp
Poisson point process on a linear network
o clickjoin
Interactive graphics to create a linear network
o superimpose
The function 'superimpose' is now generic, with methods
for ppp, psp and a default method.
o as.ppp.psp
New method for as.ppp extracts the endpoints and marks
from a line segment pattern
```

NEW DATASETS

```
o simplenet
Simple example of a linear network
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o superimposePSP
This function is now deprecated in favour of 'superimpose'
o superimpose
Now handles data frames of marks.
o plot.fv
Argument 'legendmath' now defaults to TRUE.
New argument 'legendargs' gives more control over appearance of legend.
Increased default spacing between lines in legend.
o eval.fv, with.fv
Functions computed using eval.fv or with.fv
now have better labels when plotted.
o summary functions
(Kest, Kest.fft, Kcross, Kdot, Kmulti,
Kinhom, Kcross.inhom, Kdot.inhom, Kmulti.inhom,
Lest, Lcross, Ldot,
pcf, pcfcross, pcfdot, pcfinhom, pcfcross.inhom, pcfdot.inhom,
Fest, Gest, Gcross, Gdot, Gmulti,
Jest, Jcross, Jdot, Jmulti, Iest,
localL, localK,
markcorr, markvario, markconnect, Emark, Vmark,
allstats, alltypes)
Improved plot labels.
```

BUG FIXES

```
o superimpose
If the marks components of patterns consisted of character
vectors (rather than factors or non-factor numeric vectors)
an error was triggered.
Fixed.
o plot.fv
The y axis limits did not always cover the range of values
if the argument 'shade' was used.
Fixed.
o plot.rhohat
The y axis label was sometimes incorrect.
Fixed.
o plot.rhohat
If argument 'xlim' was used, a warning was generated from 'rug'.
Fixed.
CHANGES IN spatstat VERSION 1.21-6
```

OVERVIEW

```
o A line segment pattern can now have a data frame of marks.
o Various minor extensions and alterations in behaviour
```

NEW FUNCTIONS

```
o nsegments
Number of segments in a line segment pattern
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o psp class
A line segment pattern (object of class 'psp') can now have a
data frame of marks.
o density.ppp
New argument 'adjust' makes it easy to adjust the smoothing bandwidth
o plot.envelope
If the upper envelope is NA but the lower envelope is finite,
the upper limit is now treated as +Infinity
o msr
Argument 'continuous' renamed 'density'
```

BUG FIXES

```
o [.psp
In X[W] if X is a line segment pattern and W is a polygonal window,
marks were sometimes discarded, leading to an error.
Fixed.
o [.psp
In X[W] if X is a line segment pattern and W is a rectangular window,
if the marks of X were factor values, they were converted to integers.
Fixed.
o superimposePSP
If the marks were a factor, they were mistakenly converted to integers.
Fixed.
o is.marked.ppp
Did not generate a fatal error when na.action="fatal" as described
in the help file.
Fixed.
CHANGES IN spatstat VERSION 1.21-5
```

OVERVIEW

```
o Increased numerical stability.
o New 'self-starting' feature of interpoint interactions.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o ppm
Interaction objects may now be 'self-starting'
i.e. initial parameter estimates can be computed
from the point pattern dataset.
So far, only the LennardJones() interaction
has a self-starting feature.
o LennardJones
Increased numerical stability.
New (optional) scaling argument 'sigma0'.
Interpoint distances are automatically rescaled
using 'self-starting' feature.
o vcov.ppm
New argument 'matrix.action' controls what happens when
the matrix is ill-conditioned.
Changed name of argument 'gamaction' to 'gam.action'
o rmhmodel.ppm
Default resolution of trend image has been increased.
o is.poisson.ppm
Accelerated.
o ppm, kppm, qqplot.ppm
Improved robustness to numerical error
CHANGES IN spatstat VERSION 1.21-4
```

OVERVIEW

```
o Urgent bug fix
```

BUG FIXES

```
o print.summary.ppm exited with an error message,
if the model had external covariates.
Fixed.
CHANGES IN spatstat VERSION 1.21-3
```

OVERVIEW

```
o Point process model covariates may now depend on additional parameters.
o New class of signed measures, for residual analysis.
o Miscellaneous improvements and bug fixes.
```

NEW FUNCTIONS

```
o clarkevans.test
Classical Clark-Evans test of randomness
o msr
New class 'msr' of signed measures and vector-valued measures
supporting residual analysis.
o quadrat.test.quadratcount
Method for 'quadrat.test' for objects of class 'quadratcount'
(allows a chi-squared test to be performed on quadrat counts
rather than recomputing from the original data)
o tile.areas
Computes areas of tiles in a tessellation (efficiently)
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o ppm
The spatial trend can now depend on additional parameters.
This is done by allowing spatial covariate functions
to have additional parameters: function(x, y, ...)
where ... is controlled by the new argument 'covfunargs' to ppm
o profilepl
Can now maximise over trend parameters as well as interaction parameters
o residuals.ppm
The value returned by residuals.ppm is now an object
of class 'msr'. It can be plotted directly.
o eval.im
When the argument 'envir' is used, eval.im() now recognises
functions as well as variables in 'envir'
o colourmap
The argument 'col' can now be any kind of colour data
o persp.im
The 'colmap' argument can now be a 'colourmap' object
o ppm
The print and summary methods for 'ppm' objects
now show standard errors for parameter estimates
if the model is Poisson.
o quadrat.test
The print method for 'quadrattest' objects
now displays information about the quadrats
o lurking
Improved format of x axis label
o distmap.ppp
Internal code is more robust.
```

BUG FIXES

```
o im
Did not correctly handle 1 x 1 arrays.
Fixed.
o as.mask, pixellate.ppp
Weird things happened if the argument 'eps' was set
to a value greater than the size of the window.
Fixed.
CHANGES IN spatstat VERSION 1.21-2
```

OVERVIEW

```
o New multitype hardcore interaction.
o Nonparametric estimation of covariate effects on point patterns.
o Output of 'Kmeasure' has been rescaled.
o Numerous improvements and bug fixes.
```

NEW FUNCTIONS

```
o MultiHard
multitype hard core interaction for use in ppm()
o coords<-
Assign new coordinates to the points in a point pattern
o rhohat
Kernel estimate for the effect of a spatial covariate
on point process intensity
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o as.ppp.matrix, as.ppp.data.frame
These methods for 'as.ppp' now accept a matrix or data frame
with any number of columns (>= 2) and interpret the additional
columns as marks.
o Kmeasure
The interpretation of the output has changed:
the pixel values are now density estimates.
o rmh.ppm, rmhmodel.ppm
These functions now accept a point process model
fitted with the 'MultiHard' interaction
o rmh.default, rmhmodel.default
These functions now accept the option: cif='multihard'
defining a multitype hard core interaction.
o markcorr
Now handles a data frame of marks
o varblock
Improved estimate in the case of the K function
o colourmap, lut
New argument 'range' makes it easier to specify a colour map
or lookup table
o [<-.hyperframe
Now handles multiple columns
o plot.fv
Improved y axis labels
o spatstat.options
New option 'par.fv' controls default parameters for line plotting
o rmhmodel
More safety checks on parameter values.
o quadratresample
New argument 'verbose'
o smooth.fv
Default value of 'which' has been changed.
```

BUG FIXES

```
o Kest
If the argument 'domain' was used, the resulting estimate
was not correctly normalised.
Fixed.
o Kest
The Lotwick-Silverman variance approximation was incorrectly
calculated. (Spotted by Ian Dryden and Igor Chernayavsky).
Fixed.
o plot.owin, plot.ppp
Display of binary masks was garbled if the window was
empty or if it was equivalent to a rectangle.
Fixed.
o plot.bermantest
One of the vertical lines for the Z1 test was in the wrong place.
Fixed.
o marks<-.ppx
Crashed in some cases.
Fixed.
o is.convex
An irrelevant warning was issued (for non-convex polygons).
Fixed.
CHANGES IN spatstat VERSION 1.21-1
```

OVERVIEW

```
o Confidence intervals for K-function and other statistics
o Bug fixes for smoothing and relative risk estimation
```

NEW FUNCTIONS

```
o varblock
Variance estimation (and confidence intervals)
for summary statistics such as Kest, using subdivision technique
o bw.stoyan
Bandwidth selection by Stoyan's rule of thumb.
o which.max.im
Applied to a list of images, this determines which image
has the largest value at each pixel.
o as.array.im
Convert image to array
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o smooth.ppp, markmean, sharpen.ppp, relrisk, bw.relrisk
Further acceleration achieved.
o Kest
Argument 'correction' now explicitly overrides automatic defaults
o plot.fv
More robust handling of 'shade'
```

BUG FIXES

```
o relrisk
Format of relrisk(at="points") was incorrect.
Fixed.
o bw.relrisk
Result was incorrect in the default case method="likelihood"
because of previous bug.
Fixed.
o Jdot, Jcross, Jmulti
Return value did not include the hazard function, when correction="km"
Fixed.
o Jdot, Jcross, Jmulti
Format of output was incompatible with format of Jest.
Fixed.
CHANGES IN spatstat VERSION 1.21-0
```

OVERVIEW

```
o Implemented Spatial Logistic Regression
o Implemented nonparametric estimation of relative risk
with bandwidth selection by cross-validation.
o Smoothing functions can handle a data frame of marks.
o New options in Kinhom; default behaviour has changed.
```

NEW FUNCTIONS

```
o slrm
Fit a spatial logistic regression model
o anova.slrm, coef.slrm, fitted.slrm, logLik.slrm, plot.slrm, predict.slrm
Methods for spatial logistic regression models
o relrisk
Nonparametric estimation of relative risk
o bw.relrisk
Automatic bandwidth selection by cross-validation
o default.rmhcontrol
Sets default values of Metropolis-Hastings parameters
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o smooth.ppp, markmean
These functions now accept a data frame of marks.
o Kinhom
Default behaviour has changed.
New argument 'renormalise=TRUE' determines scaling of estimator
and affects bias and variance in small samples.
o residuals.ppm
Now also computes the score residuals.
o plot.im
New argument 'ribscale'
o plot.listof, plot.splitppp
New arguments panel.begin, panel.end and panel.args
o ppp
Now checks for NA/NaN/Inf values in the coordinates
o envelope.ppm
Changed default value of 'control'
New argument 'nrep'
o qqplot.ppm
Changed default value of 'control'
```

BUG FIXES

```
o marks<-.ppp, setmarks, %mark%
A matrix of marks was accepted by ppp()
but not by these assignment functions.
Fixed.
o density.ppp, smooth.ppp, sharpen.ppp, markmean
Crashed if the bandwidth was extremely small.
Fixed.
CHANGES IN spatstat VERSION 1.20-5
```

OVERVIEW

```
o Accelerated computations of kernel smoothing.
o Implemented Choi-Hall data sharpening.
```

NEW FUNCTIONS

```
o sharpen.ppp
Performs Choi-Hall data sharpening of a point pattern
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o density.ppp, smooth.ppp
Computation has been vastly accelerated
for density(X, at="points") and smooth.ppp(X, at="points")
o Kinhom
Accelerated in case where lambda=NULL
o Vignette 'shapefiles' updated
CHANGES IN spatstat VERSION 1.20-4
```

OVERVIEW

```
o New functions for inhomogeneous point patterns
and local analysis.
o Pair correlation function for 3D point patterns
o Minor improvements and bug fixes to simulation code and image functions
```

NEW FUNCTIONS

```
o pcf3est
Pair correlation function for 3D point patterns.
o Kscaled, Lscaled
Estimator of the template K function (and L-function)
for a locally-scaled point process.
o localpcf
Local version of pair correlation function
o identify.psp
Method for 'identify' for line segment patterns.
o as.im.matrix
Converts a matrix to a pixel image
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o rMaternI, rMaternII
New argument 'stationary=TRUE' controls whether the
simulated process is stationary (inside the simulation window).
Default simulation behaviour has changed.
o im
New arguments 'xrange', 'yrange'
o envelope
Improvements to robustness of code.
```

BUG FIXES

o quadratcount If V was a tessellation created using a factor-valued image, quadratcount(X, tess=V) crashed with the error "Tessellation does not contain all the points of X". Fixed.

o [.im If Z was a factor valued image and X was a point pattern then Z[X] was not a factor. Fixed.

```
CHANGES IN spatstat VERSION 1.20-3
```

OVERVIEW

```
o minor improvements (mostly internal).
```

NEW FUNCTIONS

```
o unmark.ppx
Method for 'unmark' for general space-time point patterns
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o plot.ppx
Now handles marked patterns, in two-dimensional case
o as.psp.psp
Default value of argument 'check' set to FALSE
CHANGES IN spatstat VERSION 1.20-2
```

OVERVIEW

```
o Extensions to minimum contrast estimation.
o Bug fix in simulation of Lennard-Jones model.
o More support for distance functions.
o Changes to point process simulations.
```

NEW FUNCTIONS

```
o thomas.estpcf
Fit Thomas process model by minimum contrast using the
pair correlation function (instead of the K-function).
o matclust.estpcf
Fit Matern Cluster model by minimum contrast using the
pair correlation function (instead of the K-function).
o lgcp.estpcf
Fit log-Gaussian Cox process model by minimum contrast using the
pair correlation function (instead of the K-function).
o contour.distfun, persp.distfun
Methods for 'contour' and 'persp' for distance functions
o default.expand
Computes default window for simulation of a fitted point process model.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o kppm
Models can now be fitted using either the K-function
or the pair correlation function.
o ppm
The list of covariates can now include windows
(objects of class 'owin'). A window will be treated
as a logical covariate that equals TRUE inside the window
and FALSE outside it.
o plot.distfun
Pixel resolution can now be controlled.
o envelope.ppm, qqplot.ppm
The default value of 'control' has changed;
simulation results may be slightly different.
o rmh
Slightly accelerated.
```

BUG FIXES

```
o rmh
Simulation of the Lennard-Jones model (cif = 'lennard') was incorrect
due to an obscure bug, introduced in spatstat 1.20-1.
Fixed.
o thomas.estK, matclust.estK, lgcp.estK
The value of 'lambda' (if given)
was ignored if X was a point pattern.
Fixed.
CHANGES IN spatstat VERSION 1.20-1
```

OVERVIEW

```
o Further increases in speed and efficiency of ppm and rmh
o New pairwise interaction model
```

NEW FUNCTIONS

```
o DiggleGatesStibbard
Diggle-Gates-Stibbard pairwise interaction for use in ppm()
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o ppm
has been accelerated by a factor of 10 for the BadGey interaction.
o rmh
simulation of the Lennard-Jones model (cif='lennard')
has been greatly accelerated.
o rmh, rmhmodel.ppm
Point process models fitted by ppm() using the DiggleGatesStibbard
interaction can be simulated automatically using rmh.
```

BUG FIXES

```
o fitin
The plot of a fitted Hardcore interaction was incorrect.
Fixed.
CHANGES IN spatstat VERSION 1.20-0
```

OVERVIEW

```
o spatstat now contains over 1000 functions.
o Substantial increase in speed and efficiency
of model-fitting code.
o Changes to factor-valued images.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o ppm
has been accelerated by a factor of 10,
and can handle datasets with 20,000 points,
for the following interactions:
DiggleGratton, Fiksel, Geyer, Hardcore, Strauss, StraussHard
o predict.ppm
accelerated by a factor of 3 (when type = "cif")
with vastly reduced memory requirements
for the following interactions:
DiggleGratton, Fiksel, Geyer, Hardcore, Strauss, StraussHard
o pixel images (class "im")
The internal representation of factor-valued images has changed.
Existing objects in the old format should still work.
o im
The syntax for creating a factor-valued image has changed.
Argument 'lev' has been deleted.
o ppm
Some warnings have been reworded for greater clarity.
```

BUG FIXES

```
o [.im
Mishandled some factor-valued images.
Fixed.
o hist.im
Produced slightly erroneous output for some factor-valued images.
Fixed.
o plot.owin
Filled polygons appeared to contain criss-cross lines
on some graphics drivers.
Fixed.
o deltametric
Did not handle windows with different enclosing frames
(error message: 'dA and dB are incompatible')
Fixed.
o quadratcount
Crashed if the pattern was empty and the window was a rectangle.
(Noticed by Sandro Azaele)
Fixed.
o rNeymanScott
Crashed if the parent process realisation was empty.
(Noticed by Sandro Azaele)
Fixed.
CHANGES IN spatstat VERSION 1.19-3
```

ACKNOWLEDGEMENTS

```
o We thank David Dereudre for contributions.
```

OVERVIEW

```
o Urgent bug fix to Metropolis-Hastings for Lennard-Jones model.
o Miscellaneous additions to plotting and colour management.
```

NEW FUNCTIONS

```
o col2hex, rgb2hex, paletteindex, samecolour
Functions for converting and comparing colours.
o plot.envelope
New method for plotting envelopes.
By default the area between the upper and lower envelopes
is shaded in grey.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o plot.fasp
If the entries in the array are envelopes,
they are plotted using plot.envelope
(hence the envelope region is shaded grey).
o plot.fv
Now displays mathematical notation for each curve,
if legendmath=TRUE.
o print.fv
Now prints the available range of 'r' values
as well as the recommended range of 'r' values.
```

BUG FIXES

```
o rmh
Simulation of Lennard-Jones model was incorrect;
the simulations were effectively Poisson patterns.
(Spotted by David Dereudre.)
Fixed.
o plot.fv
Did not correctly handle formulas that included I( )
Fixed.
CHANGES IN spatstat VERSION 1.19-2
```

ACKNOWLEDGEMENTS

```
o We thank Jorge Mateu, Michael Sumner and Sebastian Luque
for contributions.
```

OVERVIEW

```
o More support for fitted point process models and pixel images.
o Improved plotting of pixel images and envelopes.
o Simulation algorithm for Lennard-Jones process.
o Improvements and bug fixes to envelopes.
o Bug fixes to Metropolis-Hastings simulation.
```

NEW FUNCTIONS

```
o pairs.im
Creates a scatterplot matrix for several pixel images.
o model.frame.ppm
Method for 'model.frame' for point process models.
o sort.im
Method for 'sort' for pixel images.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o plot.fv, plot.fasp
New argument 'shade' enables confidence intervals
or significance bands to be displayed as filled grey shading.
o LennardJones
The parametrisation of this interaction function has been changed.
o rmh, rmhmodel
These functions will now simulate a point process model
that was fitted using the LennardJones() interaction.
o rmh.default, rmhmodel.default
These functions will now simulate a point process model
with the Lennard-Jones interaction (cif='lennard').
o ecdf
This function now works for pixel images.
o dim, row, col
These functions now work for pixel images.
o order
This function now works for pixel images.
o [.im and [<-.im
The subset index can now be any valid subset index for a matrix.
o density.ppp, smooth.ppp
The return value now has attributes 'sigma' and 'varcov'
reporting the smoothing bandwidth.
o plot.im
The argument 'col' can now be a 'colourmap' object.
This makes it possible to specify a fixed mapping between
numbers and colours (e.g. so that it is consistent between
plots of several different images).
o rmh, spatstat.options
spatstat.options now recognises the parameter 'expand'
which determines the default window expansion factor in rmh.
o rmh
Improved handling of ppm objects with covariates.
o kstest
The 'covariate' can now be one of the characters "x" or "y"
indicating the Cartesian coordinates.
```

BUG FIXES

```
o model.matrix.ppm
For a fitted model that used a large number of quadrature points,
model.matrix.ppm sometimes reported an internal error about mismatch
between the model matrix and the quadrature scheme.
Fixed.
o plot.ppx
Minor bugs fixed.
o rmh
In rare cases, the simulated point pattern
included multiple points at the origin (0,0).
(Bug introduced in spatstat 1.17-0.)
Fixed.
o rmh, rmhmodel.ppm
Crashed when applied to a fitted multitype point process model
if the model involved more than one covariate image.
(Spotted by Jorge Mateu)
Fixed.
o density.psp
If any segment had zero length, the result contained NaN values.
(Spotted by Michael Sumner and Sebastian Luque.)
Fixed.
o envelope
Crashed with fun=Lest or fun=Linhom if the number of points in
a simulated pattern exceeded 3000.
Fixed.
o plot.kstest
Main title was corrupted if the covariate was a function.
Fixed.
CHANGES IN spatstat VERSION 1.19-1
```

OVERVIEW

```
o New dataset: replicated 3D point patterns.
o Improvements to Metropolis-Hastings simulation code.
o More support for hyperframes.
o Bug fixes.
```

NEW DATASETS

```
o osteo:
Osteocyte Lacunae data: replicated 3D point patterns
```

NEW FUNCTIONS

```
o rbind.hyperframe:
Method for rbind for hyperframes.
o as.data.frame.hyperframe:
Converts a hyperframe to a data frame.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o Fiksel:
Fitted point process models (class ppm) with the Fiksel()
double exponential interaction can now be simulated by rmh.
o rmh.default:
Point processes with the Fiksel interaction can now be
simulated by specifying parameters in rmh.default.
o logLik.ppm:
New argument 'warn' controls warnings.
o profilepl:
No longer issues spurious warnings.
```

BUG FIXES

```
o Hardcore, rmh:
Simulation of the 'Hardcore' process was incorrect.
The hard core radius was erroneously set to zero
so that the simulated patterns were Poisson.
Fixed.
o fitin:
A plot of the pairwise interaction function of a fitted model,
generated by plot(fitin(model)) where model <- ppm(...),
was sometimes incorrect when the model included a hard core.
Fixed.
CHANGES IN spatstat VERSION 1.19-0
```

OVERVIEW

```
o Numerous bugs fixed in the implementation of
the Huang-Ogata approximate maximum likelihood method.
o New interpoint interaction model.
```

NEW FUNCTIONS

```
o Fiksel:
new interpoint interaction: Fiksel's double exponential model.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o runifpoint, rpoispp, envelope
These functions now issue a warning if the number of random points
to be generated is very large. This traps a common error in
simulation experiments.
```

BUG FIXES

```
o predict.ppm, fitted.ppm:
Predictions and fitted values were incorrect for
objects fitted using ppm(..., method="ho").
Fixed.
o logLik, AIC:
Values of logLik() and AIC() were incorrect for
objects fitted using ppm(..., method="ho").
Fixed.
o profilepl:
Results were incorrect if the argument 'method="ho"' was used.
Fixed.
o fitin
The result of fitin() was incorrect for
objects fitted using ppm(..., method="ho").
Fixed.
o rmhcontrol:
rmhcontrol(NULL) generated an error.
Fixed.
CHANGES IN spatstat VERSION 1.18-4
```

ACKNOWLEDGEMENTS

```
o We thank Michael Sumner for contributions.
```

BUG FIXES

```
o pixellate.psp: segments shorter than one pixel width
were measured incorrectly if the 'weights' argument was present.
Fixed.
```

NEW FUNCTIONS

```
o pairdist.ppx, crossdist.ppx, nndist.ppx, nnwhich.ppx:
Methods for pairdist, crossdist, nndist, nnwhich
for multidimensional point patterns (class 'ppx')
o runifpointx, rpoisppx:
Random point patterns in any number of dimensions
o boxx:
Multidimensional box in any number of dimensions
o diameter.boxx, volume.boxx, shortside.boxx, eroded.volumes.boxx:
Geometrical computations for multidimensional boxes
o sum.im, max.im, min.im:
Methods for sum(), min(), max() for pixel images.
o as.matrix.ppx:
Convert a multidimensional point pattern to a matrix
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o plot.ppp: New argument 'zap'
o diameter: This function is now generic,
with methods for "owin", "box3" and "boxx"
o eroded.volumes: This function is now generic,
with methods for "box3" and "boxx"
CHANGES IN spatstat VERSION 1.18-3
```

ACKNOWLEDGEMENTS

```
o We thank Michael Sumner for contributions.
```

BUG FIXES

```
o pixellate.psp: segments shorter than one pixel width
were measured incorrectly. Fixed.
o fv: 'alim' not handled correctly. Fixed.
```

NEW FUNCTIONS

```
o smooth.fv:
Applies spline smoothing to the columns of an fv object.
CHANGES IN spatstat VERSION 1.18-2
```

ACKNOWLEDGEMENTS

```
o We thank Michael Sumner for contributions.
```

NEW FUNCTIONS

```
o Gfox, Jfox:
Foxall's G and J functions
o as.owin.distfun:
New method for as.owin extracts the domain of a distfun object.
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o distfun: objects of class 'distfun', when called as functions,
will now accept either two vectors (x,y) or a point pattern x.
o Hest: this function can now compute the Hanisch estimator.
It now has arguments 'r', 'breaks' and 'correction',
like other summary functions.
o Hest: new argument 'conditional'.
```

BUG FIXES

```
o pixellate.psp: Values were sometimes incorrect due to coding error.
(Spotted by Michael Sumner)
Fixed.
o kstest: Crashed if the covariate contained NA's.
Fixed.
o kstest: Crashed if X was a multitype point pattern
in which some mark values were unrepresented.
Fixed.
o lurking: Minor bug in handling of NA values.
Fixed.
o Hest: labels of columns were incorrect.
Fixed.
CHANGES IN spatstat VERSION 1.18-1
```

ACKNOWLEDGEMENTS

```
o we thank Andrew Bevan and Ege Rubak for suggestions.
```

NEW FUNCTIONS

```
o Hardcore: Hard core interaction (for use in ppm)
o envelope.pp3: simulation envelopes for 3D point patterns
o npoints: number of points in a point pattern of any kind
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o rmh.ppm, rmhmodel.ppm:
It is now possible to simulate Gibbs point process models
that are fitted to multitype point patterns using a
non-multitype interaction, e.g.
data(amacrine)
fit <- ppm(amacrine, ~marks, Strauss(0.1))
rmh(fit, ...)
o rmh.ppm, rmhmodel.ppm, rmh.default, rmhmodel.default:
Hard core models can be simulated.
o rmh.default, rmhmodel.default:
The argument 'par' is now required to be a list, in all cases
(previously it was sometimes a list and sometimes a vector).
o Fest:
Calculation has been accelerated in some cases.
o summary.pp3 now returns an object of class 'summary.pp3'
containing useful summary information. It is plotted by
'plot.summary.pp3'.
o F3est, G3est, K3est: these functions now accept
'correction="best"'
o union.owin, intersect.owin:
these functions now handle any number of windows.
o envelope.ppp, envelope.ppm, envelope.kppm:
argument lists have changed slightly
```

BUG FIXES

```
o Fest: The result of Fest(X, correction="rs") had a slightly
corrupted format, so that envelope(X, Fest, correction="rs")
in fact computed the envelopes based on the "km" correction.
(Spotted by Ege Rubak).
Fixed.
o rmh (rmh.ppm, rmhmodel.ppm):
rmh sometimes failed for non-stationary point process models,
with a message about "missing value where TRUE/FALSE needed".
(Spotted by Andrew Bevan).
Fixed.
o diagnose.ppm, lurking:
Calculations were not always correct if the model
had conditional intensity equal to zero at some locations.
Fixed.
o ppm, profilepl:
If data points are illegal under the model (i.e. if any
data points have conditional intensity equal to zero)
the log pseudolikelihood should be -Inf but was sometimes
returned as a finite value. Thus profilepl did not always
work correctly for models with a hard core.
Fixed.
o F3est, G3est:
Debug messages were printed unnecessarily.
Fixed.
CHANGES IN spatstat VERSION 1.18-0
```

ACKNOWLEDGEMENTS

```
o we thank Ege Rubak and Tyler Dean Rudolph for suggestions.
```

HEADLINES

```
o A point pattern is now allowed to have a data frame of marks
(previously the marks had to be a vector).
o Extended capabilities for 'envelope' and 'kstest'.
```

NEW FUNCTIONS

```
o pixellate.psp, as.mask.psp
Convert a line segment pattern to a pixel image or binary mask
o as.data.frame.im
Convert a pixel image to a data frame
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o A point pattern is now allowed to have a data frame of marks
(previously the marks had to be a vector).
o Many functions in spatstat now handle point patterns with
a data frame of marks.
These include print.ppp, summary.ppp, plot.ppp, split.ppp.
o finpines, nbfires, shapley:
The format of these datasets has changed.
They are now point patterns with a data frame of marks.
o envelope() is now generic, with methods for "ppp", "ppm" and "kppm".
o kstest() now handles multitype point patterns and
multitype point process models.
o nnclean() now returns a point pattern with a data frame of marks.
o plot.ppp() has new argument 'which.marks' to select one column
from a data frame of marks to be plotted.
o plot.ppp() now handles marks that are POSIX times.
o complement.owin now handles any object acceptable to as.owin.
```

BUG FIXES

```
o erosion(w) and opening(w) crashed if w was not a window.
Fixed.
o diameter() and eroded.areas() refused to work if w was not a window.
Fixed.
CHANGES IN spatstat VERSION 1.17-6
```

ACKNOWLEDGEMENTS

```
o We thank Simon Byers and Adrian Raftery for generous contributions.
```

OVERVIEW

```
o Nearest neighbour clutter removal algorithm
o New documentation for the 'fv' class.
o Minor improvements and bug fixes.
```

NEW FUNCTIONS

```
o nnclean: Nearest neighbour clutter removal for recognising features
in spatial point patterns. Technique of Byers and Raftery (1998)
[From original code by Simon Byers and Adrian Raftery,
adapted for spatstat.]
o marks.ppx, marks<-.ppx: Methods for extracting and changing marks
in a multidimensional point pattern
o latest.news: print news about the current version of the package
```

SIGNIFICANT USER-VISIBLE CHANGES

```
o news: spatstat now has a NEWS file which can be printed by
typing news(package="spatstat").
o areaGain, areaLoss: New algorithms in case exact=TRUE.
Syntax slightly modified.
o with.hyperframe:
- The result now inherits 'names' from the row names
of the hyperframe.
- New argument 'enclos' controls the environment
in which the expression is evaluated.
- The algorithm is now smarter at simplifying the result
when simplify=TRUE.
o update.ppm: Tweaked to improve the ability of ppm objects
to be re-fitted in different contexts.
```

ADVANCED USERS ONLY

```
o Documentation for the class 'fv' of function value tables
- fv: Creates an object of class 'fv'
- cbind.fv, collapse.fv: Combine objects of class 'fv'
- bind.fv: Add additional columns of data to an 'fv' object
```

BUG FIXES

```
o "$<-.hyperframe" destroyed the row names of the hyperframe.
Fixed.
o model.matrix.ppm had minor inconsistencies.
Fixed.
o ppm: The fitted coefficient vector had incorrect format
in the default case of a uniform Poisson process.
Fixed.
o plot.ppx: Crashed if the argument 'main' was given.
Fixed.
o envelope.ppp: Crashed if the object returned by 'fun'
did not include a column called "theo".
Fixed.
```