mcmc_postproc: Post-process Gibbs chain outputs.

In lgaborini/bayessource: Bayesian approach to evaluate whether two datasets come from the same population

Description

Extract and reshape MCMC samples from the posteriors for theta and W . Can be used to post-process outputs from marginalLikelihood when output.mcmc is TRUE. Notice that it performs matrix inversions on every sample of W.

Usage

mcmc_postproc(mcmc.output, compute.ML = FALSE, cumulative = TRUE)

Arguments

mcmc.output	The coda object
compute.ML	if TRUE, also compute the posterior means
cumulative	if TRUE, also compute cumulative posterior means to assess precision

Details

It is also possible to compute ML estimators for the posterior means, as well as the cumulated estimates. The results will be appended to the returned list.

Value

a named list with multidimensional arrays for W, theta, and ML estimates

See Also

Other core functions: bayessource-package, get_minimum_nw_IW(), make_priors_and_init(), marginalLikelihood_internal(), marginalLikelihood(), samesource_C(), two.level.multivariate.calculate.UC()

lgaborini/bayessource documentation built on Nov. 9, 2021, 2:10 p.m.