logL.boot: Estimate marginal likelihood from bootstrap replicates

In dosreislab/mcmc3r: Tools to work with MCMCtree

Estimate marginal likelihood from bootstrap replicates

Description

Estimate marginal likelihood from bootstrap replicates

Usage

stepping.stones.boot(R, betaf = "beta.txt", preff = "lnL")

gauss.quad.boot(R, betaf = "beta.txt", preff = "lnL")

Arguments

R	numeric, number of bootstrap replicates used
betaf	character, file with beta values
preff	character, prefix for files storing boot replicates

Details

stepping.stones.boot and gauss.quad.boot are used to calculate the marginal likelihoods on bootstrap replicates using the stepping stones and gaussian quadrature methods respectively. The replicates must have been generated using block.boot.

Value

A list with components logml, the original log-marginal likelihood estimate, logmlR, the vector of log-marginal likelihood estimates on the boostrap replicates, se and ci, the standard error and 95% credibility interval of logml calculated on the bootstrap replicates, and b, the beta values used.

See Also

block.boot, stepping.stones and gauss.quad.

dosreislab/mcmc3r documentation built on March 29, 2024, 6:45 p.m.