lAccept.ratio: Acceptance probability in the MCMC algorithm.

In lbelzile/BMAmevt: Multivariate Extremes: Bayesian Estimation of the Spectral Measure

Acceptance probability in the MCMC algorithm.

Description

Logarithm of the acceptance probability

Usage

lAccept.ratio(
  cur.par,
  prop.par,
  llh.cur,
  lprior.cur,
  dat,
  likelihood,
  proposal,
  prior,
  Hpar,
  MCpar
)

Arguments

cur.par	The current parameter in the Markov chain
prop.par	The candidate parameter
dat	An angular data set, e.g., constructed by cons.angular.dat: A matrix which rows are the Cartesian coordinates of points on the unit simplex (summing to one).
likelihood	The likelihood function. Should be of type function(x, par, log, vectorial), where log and vectorial are logical flags indicating respectively if the result is to be returned on the log-scale, and if the value is a vector of length nrow(x) or a single number (the likelihood, or the log-likelihood, for the data set x). See dpairbeta or dnestlog for templates.
proposal	The proposal function: of type function(type = c("r","d"), cur.par, prop.par, MCpar, log) . Should return the (logarithm of) the proposal density for the move cur.par --> prop.par if type == "d". If type =="r", proposal must return a candidate parameter, depending on cur.par, as a vector. See proposal.pb or proposal.nl for templates.
prior	The prior distribution: of type function(type=c("r","d"), n ,par, Hpar, log, dimData ), where dimData is the dimension of the sample space (e.g., for the two-dimensional simplex (triangle), dimData=3. Should return either a matrix with n rows containing a random parameter sample generated under the prior (if type == "d"), or the density of the parameter par (the logarithm of the density if log==TRUE. See prior.pb and prior.nl for templates.
Hpar	A list containing Hyper-parameters to be passed to prior.
MCpar	A list containing MCMC tuning parameters to be passed to proposal.

Details

lAccept.ratio is a functional: likelihood,proposal,prior are user defined functions. Should not be called directly, but through the MCMC sampler posteriorMCMC generating the posterior.

Value

The log-acceptance probability.

lbelzile/BMAmevt documentation built on April 28, 2023, 2:29 p.m.