decide: Makes the Metropolis-Hastings acceptance decision, based upon...
In nimble: MCMC, Particle Filtering, and Programmable Hierarchical Modeling

decide

R Documentation

Makes the Metropolis-Hastings acceptance decision, based upon the input (log) Metropolis-Hastings ratio

Description

This function returns a logical TRUE/FALSE value, indicating whether the proposed transition should be accepted (TRUE) or rejected (FALSE).

Usage

decide(logMetropolisRatio)

Arguments

logMetropolisRatio

The log of the Metropolis-Hastings ratio, which is calculated from model probabilities and forward/reverse transition probabilities. Calculated as the ratio of the model probability under the proposal to that under the current values multiplied by the ratio of the reverse transition probability to the forward transition probability.

Details

The Metropolis-Hastings accept/reject decisions is made as follows. If logMetropolisRatio is greater than 0, accept (return TRUE). Otherwise draw a uniform random number between 0 and 1 and accept if it is less that exp(logMetropolisRatio. The proposed transition will be rejected (return FALSE). If logMetropolisRatio is NA, NaN, or -Inf, a reject (FALSE) decision will be returned.