func_MCMC: Function to run MCMC sampling

Description

This an internal function for MCMC sampling

Usage

func_MCMC(
  survObj,
  hyperpar,
  ini,
  nIter,
  thin,
  burnin,
  S,
  method,
  MRF_2b,
  MRF_G,
  output_graph_para,
  verbose,
  cpp = FALSE
)

Value

A list object saving the MCMC results with components including 'gamma.p', 'beta.p', 'h.p', 'gamma.margin', 'beta.margin', 's', 'eta0', 'kappa0', 'c0', 'pi.ga', 'tau', 'cb', 'accept.RW', 'log.jpost', 'log.like', 'post.gamma'

Arguments

survObj: a list containing observed data from n subjects; t, di, X. See details for more information
hyperpar: a list containing prior parameter values
ini: a list containing prior parameters' initial values
nIter: the number of iterations of the chain
thin: thinning MCMC intermediate results to be stored
burnin: number of iterations to discard at the start of the chain. Default is 0
S: the number of subgroups
method: a method option from c("Pooled", "CoxBVSSL", "Sub-struct")
MRF_2b: two different b in MRF prior for subgraphs G_ss and G_rs
MRF_G: logical value. MRF_G = TRUE is to fix the MRF graph which is provided in the argument hyperpar, and MRF_G = FALSE is to use graphical model for learning the MRF graph
output_graph_para: allow (TRUE) or suppress (FALSE) the output for parameters 'G', 'V', 'C' and 'Sig' in the graphical model if MRF_G = FALSE
verbose: logical value to display the progress of MCMC
cpp: logical, whether to use C++ code for faster computation