This course develops an understanding of the Bayesian paradigm and its application in macroeconometrics with strong focus on state-of-the-art models in empirical macroeconomics.
Several topics and the empirical application of the flexible models will be covered (including programming sessions in R) such that students gain an overview of today's most recent methods and are eventually enabled to conduct own research projects applying the discussed methods. Therefore, the main topics, inter alia, cover the linear regression model (under the Bayesian paradigm), multivariate time series models (BVARs) and non-linear models. We will focus on sampling methods which allows us to estimate this large class of models (Bayesian computation).

The course will be helpful for students interested in working in academic positions and publishing their work in scientific journals. Moreover, students will gain sufficient knowledge about Bayesian computation and programming so that they are able to independently combine the covered topics to estimate their own models in R. Finally, the students can demonstrate their acquired skills by writing own research papers. Excellent papers may be extended to a Master thesis.

Attendance is mandatory (however, three missed units are tolerated).

 While the first block gives a theoretical introduction and some theoretical properties of the discussed tools, the second block covers the computational aspects and implementation in the software R. Moreover, in the third block recent solutions for problems associated with high-dimensional models and their forecasting application will be tackled.

Students should have a sound knowledge of statistics (probability, random variables, expectations, joint/conditional distributions), mathematics (linear algebra, differential/integral calculus, algebra) and basic econometrics (OLS/ML estimation). Moreover, it is expected that students are familiar with uni- and (desirable) multivariate time series models.

nikolas.kuschnig@wu.ac.at; lukas.vashold@wu.ac.at