Fitting Point Process Models via the Palm Likelihood

Functions to fit point process models using the Palm likelihood. First proposed by Tanaka, Ogata, and Stoyan (2008) , maximisation of the Palm likelihood can provide computationally efficient parameter estimation for point process models in situations where the full likelihood is intractable. This package is chiefly focused on Neyman-Scott point processes, but can also fit the void processes proposed by Jones-Todd et al. (in press) . The development of this package was motivated by the analysis of capture-recapture surveys on which individuals cannot be identified---the data from which can conceptually be seen as a clustered point process (Stevenson, Borchers, and Fewster, in press ). As such, some of the functions in this package are specifically for the estimation of cetacean density from two-camera aerial surveys.


This package provides functions for the fitting of point process models using the Palm likelihood. Maximisation of the Palm likelihood can provide computationally efficient parameter estimation in situations where the full likelihood is intractable. This package is chiefly focussed on Neyman-Scott point processes, but can also fit void processes. Estimation via the Palm likelihood was first proposed by Tanaka, Ogata, and Stoyan (2008) and further generalised by both Stevenson, Borchers, and Fewster (in review) and Jones-Todd et al. (in submission).

The development of this package was motivated by the analysis of capture-recapture surveys on which individuals cannot be identified---the data from which can conceptually be seen as a clustered point process. Some of the functions in this package are specifically for the estimation of cetacean density from two-camera aerial surveys.

Installation

The stable version of this package can be installed from CRAN:

install.packages("palm")

References

Jones-Todd, C. M., Caie, P., Illian, J., Stevenson, B. C., Savage, A., Harrison, D. J., and Bown, J. L. (in submission). Identifying unusual structures in tissue sections of colon cancer patients using point pattern analysis.

Stevenson, B. C., Borchers, D. L., and Fewster, R. M. (in revision) Cluster capture-recapture to account for identification uncertainty on aerial surveys of animal populations.

Tanaka, U., Ogata, Y., and Stoyan, D. (2008) Parameter estimation and model selection for Neyman-Scott point processes. Biometrical Journal, 50: 43--57.

News

Version 1.1.1

  • Added the `use.bobyqa' argument to fit.ns(), allowing optimisation via the bobyqa() function from the minqa package.

  • Bug fix for bootstrap simulations with no generated children.

Version 1.1.0

  • Added sim.twocamera() to simulate data from two-camera aerial surveys.

  • Added the `parents' argument to simulation functions, so that the user can specify their own parent locations.

  • Added a component containing parent locations to the output of sim.ns().

  • Bug fix for buffer edge correction with fit.twocamera().

  • Bug fix for user-specified parameter bounds with fit.void().

Version 1.0.0

  • First release of palm, after the original project was named 'nspp'.

  • Includes functions to fit Neyman-Scott point processes (including Thomas process and Matern process variants) and void processes.

  • Includes a function to estimate cetacean density from two-camera aerial surveys.

  • Includes functions to simulate from all of the above models.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("palm")

1.1.3 by Ben Stevenson, 2 months ago


https://github.com/b-steve/palm


Browse source code at https://github.com/cran/palm


Authors: Ben Stevenson <[email protected]>


Documentation:   PDF Manual  


GPL license


Imports gsl, methods, minqa, mvtnorm, R6, spatstat

Depends on Rcpp

Suggests testthat

Linking to Rcpp


See at CRAN