Syllabus

I. Course description:

The lecture covers advanced and computational intensive estimation and inference techniques with an emphasis on hands-on exercises using the econometric software Matlab.

  • Introduction to Bayesian statistics
  • Bayesian estimation of the linear regression model: closed form solutions
  • Bayesian estimation of the linear regression model: numerical solutions
  • Bayesian estimation of the nonlinear regression model: the Metropolis-Hastings algorithm
  • Bayesian estimation of VAR models with natural conjugate prior
  • Bayesian estimation of VAR models with DSGE prior (if time allows)

 

II. Prerequisities:

The course assumes knowledge of the topics taught in Advanced Statistics, Econometrics I and Econometrics II.

 

III. Exam:

  • 5 LP
  • written exam (Date: see UniVis)

 

IV. Literature:

Main textbooks (for details see the handouts for each lecture):

  • Koop, G. (2003), Bayesian Econometrics, Wiley.
  • Koop, G., D.J. Poirier, J.L. Tobias (2007) Bayesian Econometric Methods, Cambridge University Press.