Special fields of econometrics: Bayesian Econometrics
- The course is usually offered in winter semester.
- In addition to the lecture exercises are offered where mathematical problems of the lecture are discussed and solved. It is suggested that students prepare the tasks beforehand.
- Times of lectures and exercises can be found on KLIPS2.0.
Contents and Goals
Methods and concepts of Bayesian inference for econometric models will be discussed.
Students will learn how to apply Bayesian methods to linear regression and time series models . The lecture also treats the implementation of Monte-Carlo Integration (MCMC and Importance Sampling) for the analysis of posterior distributions. The students will be able to compare models, forecast and test through Bayesian methods and can conduct Bayesian analyses independently
Contents and Goals are:
- Principles of Bayesian Econometrics
- Bayesian Estimators and numerical integration
- Importance Sampling and Markov-Chain-Monte-Carlo
- Linear regression for with conjugated priors
- Linear regression for non-conjugated priors
- Linear regression with generalized covariance structures
- Time series models
- Models with discrete dependent variables
In computer exercises the students will apply these methods to appropriate data sets.