grwmrfi: Graph Random Walk-based Metropolis-Hastings on Interaction...

In Freguglia/mrf2dbayes: Bayesian Analysis of Markov Random Fields on 2d Lattices

Graph Random Walk-based Metropolis-Hastings on Interaction Structures

Description

Metropolis-Hastings algorithm over the space of interaction structures to be used as a Bayesian model selection tool.

Usage

grwmrfi(
  z,
  llapprox,
  nsamples = 10000,
  nbatch = 10,
  first_batch = 1000,
  sdprior = 2,
  init_mrfi = mrfi(1),
  verbose = interactive()
)

Arguments

z	The observed random field.
llapprox	A llapprox object based on the maximal interaction structure.
nsamples	Number of MCMC samples.
nbatch	Number of samples from the prior distribution in each update of the acceptance ratios.
sdprior	Sample Deviation of the Normal distributions used as prior.

Value

An object of class grw_out

Freguglia/mrf2dbayes documentation built on Jan. 19, 2024, 11:21 p.m.