Leave-One-Out cross-validation and WAIC for Bayesian models
This package provides an implementation of efficient approximate leave-one-out (LOO) cross-validation for Bayesian models fit using Markov chain Monte Carlo, as described in doi:10.1007/s11222-016-9696-4. 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.
| System | Target | Derivation | Build status |
|---|---|---|---|
| x86_64-linux | /gnu/store/brsglackpyvs4zad319400g01fzi4637-r-loo-2.4.0.drv | ||
| mips64el-linux | /gnu/store/h455x88bm8j8v36did1rgzh84ny07kaq-r-loo-2.4.0.drv | ||
| i686-linux | /gnu/store/fjfd7lmzy9hgcw9li3m19ayx50h1mdrb-r-loo-2.4.0.drv | ||
| i586-gnu | /gnu/store/21m2hwjlj1qhx9hlny8pvcwr7zamfvzs-r-loo-2.4.0.drv | ||
| armhf-linux | /gnu/store/1sl570kfgrn4zdjzmxp0imcqw8bzc7my-r-loo-2.4.0.drv | ||
| aarch64-linux | /gnu/store/mn3xkswmmnyxbmlwxf797nq66a8icgar-r-loo-2.4.0.drv |
| Linter | Message | Location |
|---|---|---|
| No lint warnings ✓ | ||