Bayesian Econometrics for Business and Economics

COURSE OBJECTIVE
This course in the minor Applied Econometrics is targeted at Bachelor Econometrics students and Bachelor students with different backgrounds who have already had an introduction to programming and econometrics/statistics. The objective is to acquaint the student with Bayesian statistics and applications thereof to econometric problems, using advanced computational methods.

COURSE CONTENT
This course (named Computational Econometrics (E_EOR3_CE) in the past academic years) will cover Bayesian statistics where the topics include the prior and posterior density, Bayesian hypothesis testing, Bayesian prediction, and Bayesian Model Averaging for forecast combination. Several models will be considered, including the Bernoulli/binomial distribution, the Poisson distribution and the normal distribution. Obviously, attention will be paid to the Bayesian analysis of linear regression models. Also simple time series models will be considered. An important part of the courses is the treatment of simulation-based methods such as Markov chain Monte Carlo (Gibbs sampling, data augmentation, Metropolis-Hastings method) and Importance Sampling, that are often needed to compute Bayesian estimates and predictions and to perform Bayesian tests.

TEACHING METHODS
Lectures and exercises in the computer lab.

TYPE OF ASSESSMENT
Final written exam – Individual assessment.
Exercises - groups of 1 or 2 students.

RECOMMENDED BACKGROUND KNOWLEDGE
Programming, Econometrics I, Numerical Methods.