rautologistic: Return a perfect sample from a centered autologistic model.

In donaldmusgrove/ngspatial: Fitting the Centered Autologistic and Sparse Spatial Generalized Linear Mixed Models for Areal Data

Description

Return a perfect sample from a centered autologistic model.

Usage

rautologistic(X, A, theta)

Arguments

X	the design matrix.
A	the adjacency matrix for the underlying graph. The matrix need not be binary, but it must be numeric and symmetric.
theta	the vector of parameter values: θ = (β', η)'.

Details

This function implements a perfect sampler for the centered autologistic model. The sampler employs coupling from the past.

Value

A vector that is distributed exactly according to the centered autologistic model with the given design matrix and parameter values.

References

Moller, J. (1999) Perfect simulation of conditionally specified models. Journal of the Royal Statistical Society, Series B, Methodological, 61, 251–264.

Propp, J. G. and Wilson, D. B. (1996) Exact sampling with coupled Markov chains and applications to statistical mechanics. Random Structures and Algorithms, 9(1-2), 223–252.

donaldmusgrove/ngspatial documentation built on May 15, 2019, 10:37 a.m.