Aim: Getting knowledge of the most important and well-known computational methods from Bayesian statistics, like Metropolis-Hastings-, Importance Sampling-,  Gibbs Sampling-, INLA-, Neal-, Reversible-Jump Algorithm, and implementing and using those for a diverse set of statistical problems.

Lectures and exercises. Presence is needed.

Bayes TheoremMetropolis-Hastings-AlgorithmGibbs-SamplingRevesible Jump AlgorithmINLA,Neal's Algorithm for nonparametric Dirichlet process priors.

Bayesian Statistics and/or Decision TheoryLink auf weitere InformationenSkript in Moodle

Oral examination at the end of semester, exercises from week to week, contributions of students during lecture/exercise

Topics of the lectures/exercises

To pass the exam 50% of the questions during oral examination  must be answered with "sehr gut", 50% of the exercises must have been done, the student should contribute during discussions and not be absent more than 2 times.Negative partial performance is allowed to be repeated.