Functions for fitting and plotting SITAR (Super
Imposition by Translation And Rotation) growth curve models. SITAR is
a shape-invariant model with a regression B-spline mean curve and
subject-specific random effects on both the measurement and age
scales. The model was first described by Lindstrom (1995)
Growth curve analysis
Changes in Version 1.1.1
o trim (new) option in plot.sitar to remove unsightly long lines from plots.
o For trim to work, mplot now allows rows with missing data.
o apv_se (new) bootstraps standard errors for peak velocity (pv) and age at pv.
o getPeakTrough now uses xy.coords and returns NA if no turning points.
o Fix several bugs in plot.sitar, involving subset with predict, dashed line for velocity, and axis 4 etc.
o BREAKING CHANGE - options 'dv' with subset in plot.sitar now work as they should, showing mean curves for the subset selected.
o predict.sitar improved so individual velocity curves (option V) now plot correctly when y and/or t are transformed.
o Fix bugs in xyadj improving the defaults for y and id, and making abc a data frame and adding missing columns.
o msMaxIter default in nlmeControl doubled to 100.
o getData.sitar now based on getData.nlme not getData.lme.
o LMS2z now requires 'measure' to be character, changing example accordingly. Also the specification of the sex argument has been improved and extended.
Changes in Version 1.1.0
o plot.sitar now allows data output for plotting in ggplot2 etc.
o plot.sitar now applies apv to multiple curves (options D and V).
o Fix bug in plot.sitar with options dv.
o Add vignette Fitting models in SITAR.
o Add berkeley dataset.
o cLMS and zLMS now return a matrix if z or x are matrices.
o LMS2z now returns a matrix if y is a matrix.
o Fix bug in z2cent for 11th, 12th and 13th centiles.
o pdLMS (new) plots density function(s) of Box-Cox transformed variable(s).
o mplot now omits rows with missing data.
o predict.sitar now recognises special case of .x and .id in newdata.
Changes in Version 1.0.10
o getPeakTrough (new) identifies peaks and troughs of a curve (used to improve code for age at peak velocity - replaces makess).
o AICadj and BICadj now adjust for subset, and code improved.
o dfpower (new) tabulates BIC/AIC for SITAR models by degrees of freedom and/or xy power transformations.
o getL (new) extracts the power transform of a variable in an expression.
o dfset (new) identifies optimal degrees of freedom for a natural spline curve.
o Improve label handling in plot.sitar.
o Fix bug in update.sitar with df and xoffset.
o Fix bug in predict.sitar when b.formula = ~covariate - 1.
o Fix bug in predict.sitar with abc.
o Constrain df to be >1 in sitar.
o Fix bug in sitar with make.names.
Changes in Version 1.0.9
o Fix bug in sitar with subset.
o Improve ifun call, code and documentation, adding verbose arg and returning varname as attribute.
o Reorder args in xyadj.
o Fix bug in y2plot with par(mar).
o Add lag, differences, sort and keepNA to diffid args.
o Fix bug in predict.sitar concerning id in newdata.
o Improve handling of ... args in plot.sitar with D and V options.
Changes in Version 1.0.8
o timegap (new) indexes equally spaced ages, to simplify binning age into age groups.
o Use dynGet instead of get in BICadj.
o Improve handling of y2 axis in y2plot.
o Fix bug in plot.sitar introduced in 1.0.7.
Changes in Version 1.0.7
o Add github URL to DESCRIPTION.
o Documentation and NAMESPACE now generated by Roxygen2, and S3 methods no longer visible.
o Extend ifun to handle cospi, sinpi and tanpi, and improve documentation.
o Extend predict.sitar to handle deriv 2 (acceleration).
o Extend sitar to allow functions in a.formula, b.formula and c.formula. Improve documentation for this case.
o Fix bug in sitar where the start vector is the wrong length.
o Fix bug in predict.sitar involving default value of yfun argument.
o Fix bug in predict.sitar for when a.formula, b.formula and c.formula involve a single variable.
Changes in Version 1.0.6
o Tidied up code in predict.sitar and xyadj, altering the defaults for abc, xfun and yfun. The asList argument in predict.nlme and level == 0:1 now work correctly.
o Fixed a bug in predict.sitar involving covariates in newdata (Costanza Pizzi). Factors in newdata are now represented as = rather than = [01] as before.
o Fixed a bug in plot.sitar involving subset with options d and v (Costanza Pizzi).
o Fixed a bug in plot.sitar involving subset with options D and V.
Changes in Version 1.0.5
o xoffset and bstart rationalised in sitar and update.sitar. Now xoffset defaults to mean(x) and bstart defaults to xoffset, leading to greater stability in model fitting. This is a more complete solution to issue 2 in 1.0.4. Note that models fitted in previous versions need to be refitted.
Changes in Version 1.0.4
o update.sitar code updated and simplfied.
o in sitar and update.sitar the offset for knots and bounds changed from bstart to mean(x) (suggestion of Jeroen Sichien).
o LMS2z loses data argument.
o LMS2z, cLMS and zLMS now return a vector or a matrix.
o predict.sitar and plot.sitar now create function fitnlme on the fly when it's missing.
o sitar handling for weights commented out.
o ifun bugs fixed and code simplified.
o man pages updated.
Changes in Version 1.0.3
o The heights database had age at menarche added.
o In plot.sitar ifun was used to automatically back-transform transformations of x and/or y in the sitar model.
o ifun (new) inverts an expression defining a data transformation.
o xyadj (new) adjusts x and y variables for SITAR random effects.
o predict.sitar was extended with a deriv argument to give predicted velocity.
o getCovariate and anova methods for sitar were added.
o In plot.sitar new options D and V provide spline curves of individual distance and velocity curves.
o In sitar and plot.sitar bugs were fixed and code simplified by use of predict.sitar, xyadj and ifun.
Changes in Version 1.0.2
o In DESCRIPTION the title and description were corrected, and Suggests was changed to Imports.
o In NAMESPACE lines.sitar and print.summary.sitar were added to S3 methods and splines was added to import (both previously omitted in error).
o predict, getVarCov and getData methods for sitar were added.
o The sitar command was rewritten to save the function fitnlme, for use with predict. As a result the hidden file .fitnlme is no longer created.
o The plot.sitar command now uses predict to control the number of points when drawing spline curves, and any covariate values default to zero.
o LMSfit was added.
o lms2z was renamed LMS2z for consistency.
o The changes in 1.0.1 to the graphical options xaxsd and yaxsd to deal with log scales were corrected.
o The man files were updated.
Changes in Version 1.0.1
o The environment for reading the call in sitar, plot.sitar and lines.sitar was corrected.
o The graphical options xaxsd and yaxsd were extended to deal with log scales.
Changes in Version 1.0
o First CRAN release of package "sitar" for growth curve analysis.