This course is targeted toward PhD- and doctoral students who have already a profound knowledge in Bayesian methods. The goal of the course is to enhance this knowledge by studying and discussing papers in class on topics that are of particular to advanced PhD-students. These topics will include, among others

•     Bayesian inference in high-dimensional models
•     Recent advanced in MCMC and sequential Monte Carlo
•     Emerging methods for state space models
•     Modelling high-dimensional covariance matrices
•     Bayesian non-parametric statistics

Additional topics can be suggested by the participants.

The course provides a gateway for PhD and doctoral students to enhance their knowledge in Bayesian econometrics. The students will gain access to advanced topics of Bayesian inference through studying recently published leading papers in these fields as a group. The in-class discussion will allow students to obtain a quick and in-depth understanding of a broad range of areas. With this knowledge in mind, the students be able to judge what aspects of this research is relevant for their PhD-project.

A minimum of 80% attendance is required.

Leading papers in a particular area will be made available to the participants a week before the course. A summary of these papers will be presented by the participants, followed by an intense in class-discussion of the papers, their methods and applications, with a special focus on their relevance for the participants.  

Grading will be based on (a) an in-class presentation (75%) , (b) a written summary of the relevance of a specific topic for the student's PhD-project (15%) and (c) contribution  to in-class discussion (10%)

This is an advanced course for students who have already a profound knowledge in Bayesian modelling (e.g. regression analysis, TVP models), estimation (in particular derivation of posterior densities and MCMC sampling) and Bayesian variable and model selection (e.g. Bayes factors, shrinkage priors).

This is an advanced course for students who have already a profound knowledge in Bayesian modelling (e.g. regression analysis, TVP models), estimation (in particular derivation of posterior densities and MCMC sampling) and Bayesian variable and model selection (e.g. Bayes factors, shrinkage priors).

Students who want to learn more about Bayesian inference are welcome to enroll in the introductory course Bayesian Econometrics I in WS 2021/22 and the follow-up course in Bayesian Econometrics II in SS 2022.