loo.hsstan: Predictive information criteria for Bayesian models

In hsstan: Hierarchical Shrinkage Stan Models for Biomarker Selection

Predictive information criteria for Bayesian models

Description

Compute an efficient approximate leave-one-out cross-validation using Pareto smoothed importance sampling (PSIS-LOO), or the widely applicable information criterion (WAIC), also known as the Watanabe-Akaike information criterion.

Usage

## S3 method for class 'hsstan'
loo(x, cores = getOption("mc.cores"), ...)

## S3 method for class 'hsstan'
waic(x, cores = getOption("mc.cores"), ...)

Arguments

x	An object of class hsstan.
cores	Number of cores used for parallelisation (the value of options("mc.cores") by default).
...	Currently ignored.

Value

A loo object.

Examples

# continued from ?hsstan
loo(hs.biom)
waic(hs.biom)

hsstan documentation built on June 22, 2024, 12:19 p.m.