Paquet : r-cran-loo (2.8.0-1)

[ Paquet source : r-cran-loo  ]

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.

Autres paquets associés à r-cran-loo

• dep: r-api-4.0

  paquet virtuel fourni par r-base-core

• dep: r-cran-checkmate

  vérifications rapides et polyvalentes d’arguments pour GNU R

• dep: r-cran-matrixstats (>= 0.52)

  GNU R methods that apply to rows and columns of a matrix

• dep: r-cran-posterior (>= 1.5.0)

  outils de GNU R pour travailler avec des distributions a posteriori

• rec: r-cran-bayesplot (>= 1.7.0)

  GNU R plotting for bayesian models

• rec: r-cran-brms (>= 2.10.0)

  GNU R Bayesian regression models using 'Stan'

• rec: r-cran-ggplot2

  implementation of the Grammar of Graphics

• rec: r-cran-knitr

  GNU R package for dynamic report generation using Literate Programming

• rec: r-cran-rmarkdown

  convert R markdown documents into a variety of formats

• rec: r-cran-rstan

  GNU R interface to Stan

• rec: r-cran-rstanarm (>= 2.19.0)

  GNU R bayesian applied regression modeling via stan

• rec: r-cran-rstantools

  tools for developing GNU R packages interfacing with 'Stan'

• rec: r-cran-spdep

  GNU R spatial dependence: weighting schemes, statistics and models

• rec: r-cran-testthat (>= 2.1.0)

  GNU R testsuite

Télécharger r-cran-loo

Télécharger pour toutes les architectures proposées

Architecture	Taille du paquet	Espace occupé une fois installé	Fichiers
all	2 999,2 ko	3 959,0 ko	[liste des fichiers]