brms (version 2.1.0)

add_ic: Add information criteria and fit indices to fitted model objects

Description

Add information criteria and fit indices to fitted model objects

Usage

add_ic(x, ...)
add_ic(x, ...) <- value
# S3 method for brmsfit
add_ic(x, ic = "loo", ...)

Arguments

x

An R object typically of class brmsfit.

...

Further arguments passed to the underlying functions computing the information criteria.

ic, value

Names of the information criteria / fit indices to compute. Currently supported are "loo", "waic", "kfold", "R2" (R-squared), and "bridge" (log marginal likelihood).

Value

An object of the same class as x, but with information criteria added for later usage.

Examples

# NOT RUN {
fit <- brm(count ~ Trt, epilepsy, poisson())
# add both LOO and WAIC at once
fit <- add_ic(fit, ic = c("loo", "waic"))
print(fit$loo)
print(fit$waic)
# }
# NOT RUN {
# }