BayesComm-package {BayesComm}R Documentation

Bayesian community ecology analysis

Description

BayesComm fits Bayesian multivariate binary (probit) regression models for analysis of ecological communities. These models can be used to make inference about underlying inter-species interactions in communities and to separate the effects of environmental covariates and inter-species interactions on community assembly. This package accompanies the paper (in preparation) by Golding et al. (2013) and is based on a model described by Edwards and Allenby (2003).

Details

Package: BayesComm
Type: Package
Version: 0.1-1
Date: 2014-03-07
License: GPL (>=2)

BayesComm models take as input a matrix of species presence/absence records and optionally a matrix of environmental covariates. BC is the main function for setting up models. It is a wrapper function to BCfit and returns a bayescomm object. bayescomm objects have associated summary, plot, print, window and residuals functions. Functions are also provided to calculate Deviance Information Criteria (DIC) and run a deviance partitioning procedure on model outputs (devpart).

Full details of formulation of the model are given in Golding et al. (2013).

Author(s)

Nick Golding <nick.golding@zoo.ox.ac.uk> \& Dave Harris

References

Golding (2013) Mapping and understanding the distributions of potential vector mosquitoes in the UK: New methods and applications. (Chapter 3) http://dx.doi.org/10.6084/m9.figshare.767289
Edwards, Y., Allenby, G. (2003) Multivariate analysis of multiple response data. Journal of Marketing Research, 40 (3) 321-34.

See Also

BC, BCfit, window.bayescomm, plot.bayescomm, print.bayescomm, summary.bayescomm, residuals.bayescomm, DIC, devpart,


[Package BayesComm version 0.1-2 Index]