kfold-generic

kfold

is.kfold

Arguments to pass to specific methods.

For developers of modeling packages, loo includes a generic function
<code>kfold</code> so that methods may be defined for K-fold CV without name
conflicts between packages. See, e.g., the <code>kfold.stanreg</code> method in
rstanarm and the <code>kfold.brmsfit</code> method in brms.

Efficient approximate leave-one-out cross-validation (LOO)
for Bayesian models fit using Markov chain Monte Carlo. The approximation
uses Pareto smoothed importance sampling (PSIS), a new procedure for
regularizing importance weights. As a byproduct of the calculations, we also
obtain approximate standard errors for estimated predictive errors and for
the comparison of predictive errors between models. The package also
provides methods for using stacking and other model weighting techniques
to average Bayesian predictive distributions.

Jonah Gabry

Efficient Leave-One-Out Cross-Validation and WAIC for Bayesian
Models

Aki Vehtari

Andrew Gelman

Yuling Yao

Paul-Christian B<c3><bc>rkner

Ben Goodrich

Juho Piironen

Mans Magnusson

kfold-generic function

Generic function for K-fold cross-validation for developers — kfold-generic

Generic function for K-fold cross-validation for developers

kfold-generic: Generic function for K-fold cross-validation for developers

Description

Usage

Arguments

Value