[ 原始碼： r-cran-loo ]
套件：r-cran-loo（2.0.0-2）
GNU R leave-one-out cross-validation and WAIC for Bayesian models
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, it is possible as well to 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.
其他與 r-cran-loo 有關的套件
|
|
|
|
-
- dep: r-api-3.5
- 本虛擬套件由這些套件填實： r-base-core
-
- dep: r-base-core (>= 3.5.0-5)
- GNU R core of statistical computation and graphics system
-
- dep: r-cran-matrixstats (>= 0.52)
- GNU R methods that apply to rows and columns of a matrix
-
- sug: libgdal-dev
- Geospatial Data Abstraction Library - Development files
-
- sug: r-cran-bayesplot (>= 1.5.0)
- GNU R plotting for bayesian models
-
- sug: r-cran-knitr
- GNU R package for dynamic report generation using Literate Programming
-
- sug: r-cran-rmarkdown
- convert R markdown documents into a variety of formats
-
- sug: r-cran-rstan
- GNU R interface to Stan
-
- sug: r-cran-rstantools
- tools for developing GNU R packages interfacing with 'Stan'
-
- sug: r-cran-testthat
- GNU R testsuite