sampleAlpha: Sample alpha conditional on partition and K using an...

In telescope: Bayesian Mixtures with an Unknown Number of Components

Sample alpha conditional on partition and K using an Metropolis-Hastings step with log-normal proposal.

Description

Sample \alpha conditional on the current partition and value of K using an Metropolis-Hastings step with log-normal proposal.

Usage

sampleAlpha(N, Nk, K, alpha, s0_proposal, log_pAlpha)

Arguments

N	A number; indicating the sample size.
Nk	An integer vector; indicating the group sizes in the partition.
K	A number; indicating the number of components.
alpha	A numeric value; indicating the value for \alpha.
s0_proposal	A numeric value; indicating the standard deviation of the random walk.
log_pAlpha	A function; evaluating the log prior of \alpha.

Value

A named list containing:

• "alpha": a numeric, the new \alpha value.

• "acc": logical indicating acceptance.

telescope documentation built on April 4, 2025, 2:40 a.m.