Installation
About
Efficient approximate leave-one-out cross-validation (LOO) for Bayesian models fit using Markov chain Monte Carlo, as described in Vehtari, Gelman, and Gabry (2017) 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.
Citation | loo citation info |
mc-stan.org/loo/ | |
discourse.mc-stan.org | |
System requirements | pandoc (>= 1.12.3), pandoc-citeproc |
Bug report | File report |
Key Metrics
Downloads
Yesterday | 2.019 0% |
Last 7 days | 9.427 -31% |
Last 30 days | 50.132 +16% |
Last 90 days | 123.902 +5% |
Last 365 days | 514.228 -17% |
Material
In Views
Vignettes
Depends
R | ≥ 3.1.2 |