Bayesian methods and concepts: conditional probability, one-parameter and multiparameter models, prior distributions, hierarchical and multi-level models, predictive checking and sensitivity analysis, model selection, linear and generalized linear models, multiple testing and high-dimensional data, mixtures, non-parametric methods. Case studies of applied modeling. In-depth computational implementation using Markov chain Monte Carlo and other techniques. Basic theory for Bayesian methods and decision theory. The selection of topics may vary from year to year.

Repeat Rules

Course is not repeatable for credit.