DGPE PhD course: Bayesian Analysis of DSGE models

Lecturer: Professor Frank Schorfheide, University of Pennsylvania

2014.01.03 | Solveig Nygaard Sørensen

Date Mon 02 Jun Tue 03 Jun
Time 10:00    16:00
Location Fuglesangs Allé 4, 8210 Aarhus V, building 2610, room S313 A

The lectures will discuss recent advances in the literature on the econometric analysis of Dynamic Stochastic General Equilibrium (DSGE) models, covering both methods and applications. We begin with an introduction to Bayesian inference. We proceed with the estimation of linearized as well as nonlinear DSGE models and review algorithms to generate draws from the posterior distribution of DSGE model parameters. Once these parameter draws are obtained the DSGE models can be used to provide quantitative answers to a variety of questions, e.g. about the sources of business cycle fluctuations, relative importance of endogenous propagation mechanisms, the effects of monetary and fiscal policy interventions. We present tools to evaluate the fit of DSGE models, review the forecasting performance of estimated DSGE models, and discuss novel methods of incorporating external information (about the current state of the economy and the long-run outlook) into DSGE model forecasts. Finally, we consider empirical models that relax some of the restrictions imposed by DSGE models. These specifications include VARs with priors derived from DSGE models, DSGE models that are embedded in state-space models, and mixtures of DSGE models. The lectures include practical MATLAB exercises that illustrate how to implement the estimation methods.


  • Registration via webshop (closed)

The course is free of charge for DGPE members from AU, KU, CBS, SDU, and Nordic universities. The course fee is EUR 200 for other participants.


Lecturer: Professor Frank Schorfheide
University of Pennsylvania
Email: schorf@ssc.upenn.edu

Administrative support: Solveig Nygaard Sørensen, sns@creates.au.dk

DGPE Courses