performance: looic – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

looic

LOO-related Indices for Bayesian regressions.

Description

Compute LOOIC (leave-one-out cross-validation (LOO) information criterion) and ELPD (expected log predictive density) for Bayesian regressions.

Usage

looic(model, verbose = TRUE)

Arguments

`model`	A Bayesian regression model.
`verbose`	Toggle off warnings.

Value

A list with four elements, the ELPD, LOOIC and their standard errors.

Examples

if (require("rstanarm")) {
  model <- stan_glm(mpg ~ wt + cyl, data = mtcars, chains = 1, iter = 500, refresh = 0)
  looic(model)
}

performance

Assessment of Regression Models Performance

v0.7.1

GPL-3

Authors

Daniel Lüdecke [aut, cre] (<https://orcid.org/0000-0002-8895-3206>), Dominique Makowski [aut, ctb] (<https://orcid.org/0000-0001-5375-9967>), Mattan S. Ben-Shachar [aut, ctb] (<https://orcid.org/0000-0002-4287-4801>), Indrajeet Patil [aut, ctb] (<https://orcid.org/0000-0003-1995-6531>), Philip Waggoner [aut, ctb] (<https://orcid.org/0000-0002-7825-7573>), Vincent Arel-Bundock [ctb] (<https://orcid.org/0000-0003-2042-7063>)

Initial release