stan-dev/loo: Efficient Leave-One-Out Cross-Validation and WAIC for Bayesian Models
Version 1.1.0

Efficient approximate leave-one-out cross-validation (LOO) using 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. We also compute the widely applicable information criterion (WAIC).

Getting started

Package details

MaintainerJonah Gabry <[email protected]>
LicenseGPL (>=3)
Version1.1.0
URL http://mc-stan.org/ https://groups.google.com/forum/#!forum/stan-users
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
install.packages("devtools")
library(devtools)
install_github("stan-dev/loo")
stan-dev/loo documentation built on Sept. 12, 2017, 11:26 p.m.