baggr (version 0.7.8)

loo_compare: Compare LOO CV models

Description

Given multiple loocv outputs, calculate differences in their expected log predictive density.

Usage

loo_compare(...)

Value

Returns a series of comparisons in order of the arguments provided as Model 1 - Model N for N loocv objects provided. Model 1 corresponds to the first object passed and Model N corresponds to the Nth object passed.

Arguments

...

A series of baggr_cv objects passed as arguments, with a minimum of 2 arguments required for comparison. baggr_cv objects can be created via the loocv function. In instances where more than 2 arguments are passed, the first model will be compared sequentially to all other provided models. Arguments can be passed with names (see example below).

See Also

loocv for fitting LOO CV objects and explanation of the procedure; loo package by Vehtari et al (available on CRAN) for a more comprehensive approach

Examples

if (FALSE) {
# 2 models with more/less informative priors -- this will take a while to run
cv_1 <- loocv(schools, model = "rubin", pooling = "partial")
cv_2 <- loocv(schools, model = "rubin", pooling = "partial",
              prior_hypermean = normal(0, 5), prior_hypersd = cauchy(0,2.5))
loo_compare("Default prior"=cv_1,"Alternative prior"=cv_2)
}