Run main MCMC

Run the main MALECOT MCMC. Model parameters are taken from the current active parameter set, and MCMC parameters are passed in as arguments. All output is stored within the project.

run_mcmc(project, K = NULL, precision = 0.01, burnin = 1000,
  samples = 1000, rungs = 1, GTI_pow = 3, auto_converge = TRUE,
  converge_test = 100, solve_label_switching_on = TRUE,
  coupling_on = TRUE, cluster = NULL, pb_markdown = FALSE,
  store_acceptance = TRUE, store_raw = TRUE, silent = FALSE)

Arguments

project	a MALECOT project, as produced by the function `malecot_project()`
K	the values of K that the MCMC will explore
precision	the level of precision at which allele frequencies are represented in the bi-allelic case. This allows the use of look-up tables for the likelihood, which significantly speeds up the MCMC. Set to 0 to use exact values (up to C++ "double" precision) rather than using look-up tables
burnin	the number of burn-in iterations
samples	the number of sampling iterations
rungs	the number of temperature rungs
GTI_pow	the power used in the generalised thermodynamic integration method. Must be greater than 1.1
auto_converge	whether convergence should be assessed automatically every `converge_test` iterations, leading to termination of the burn-in phase. If `FALSE` then the full `burnin` iterations are used
converge_test	test for convergence every `convergence_test` iterations if `auto_converge` is being used
solve_label_switching_on	whether to implement the Stevens' solution to the label-switching problem. If turned off then Q-matrix output will no longer be correct, although evidence estimates will be unaffected.
coupling_on	whether to implement Metropolis-coupling over temperature rungs
cluster	option to pass in a cluster environment (see package "parallel")
pb_markdown	whether to run progress bars in markdown mode, in which case they are updated once at the end to avoid large amounts of output
store_acceptance	whether to store acceptance rates for all parameters updated by Metropolis-Hastings. Proposal distributions are tuned adaptively with a target acceptance rate of 23%
store_raw	whether to store raw MCMC output in addition to summary output. Setting to FALSE can considerably reduce output size in memory
silent	whether to suppress all console output

Examples

# TODO

Arguments

Examples

Contents