LOO-adjusted R2 — r2_loo • performance

Compute LOO-adjusted R2.

r2_loo(model, verbose = TRUE)

Arguments

model	A Bayesian regression model.
verbose	Toggle off warnings.

Value

The LOO-adjusted R2 for model, as numeric value.

Details

Unlike r2_bayes, which returns an "unadjusted" R2 value, r2_loo() calculates a LOO-adjusted R2, which comes conceptionally closer to an "adjusted" R2 measure.

Examples

if (require("rstanarm")) {
  model <- stan_glm(mpg ~ wt + cyl, data = mtcars, chains = 1, iter = 500, refresh = 0)
  r2_loo(model)
}
#> Warning: Some Pareto k diagnostic values are slightly high. See help('pareto-k-diagnostic') for details.
#> LOO-adjusted R2 
#>       0.7908119