Résumé : The tutorial covers cross-validation, and projection predictive approaches for model assessment, selection and inference after model selection and Bayesian stacking for model averaging. The talk is accompanied with R notebooks using rstanarm, bayesplot, loo, and projpred packages.

Mots-Clés : Bayesian computation; stacking; predictive distribution; model assessment; model selection; leave-one-out cross-validation (LOO)