Bayesian estimation of dsge models

Matlab programming

Course contents
This course covers some useful tools needed to solve, simulate and/or estimate micro-founded macroeconomic dynamic stochastic general equilibrium (DSGE) models. This course mainly focuses on stochastic models aimed at explaining business cycle fluctuations.

The course is organized around two objectives:

  • to acquire a sufficient theoretical knowledge to simulate and estimate macroeconomic models
  • to implement some of these methods through Matlab programming.

Point (i) contains a theoretical presentation of methods necessary to estimate and evaluate DSGE models. In particular bayesian methods and state space models are presented together with Markov chain Monte Carlo algorithms (MCMC)

In order to handle point (ii), we will begin with a brief introduction on Matlab use. Then, simulation and estimation of model are done by programming or by using Dynare.

Topics

  • A primer on Bayesian econometrics
  • Introduction to Markov chain Monte Carlo methods
  • State-space models
  • Application to DSGE models
  • Matlab examples

Prerequisites
A basic knowledge of multivariate time series, statistics and simulation methods.

Learning outcomes
The main objective is to develop skills to estimate, analyze and validate dynamic stochastic general equilibrium models.

Teaching methods
Part of the class will be devoted to the discussion of some theoretical issues related to the topics. Each theoretical topic will be integrated by examples and applications.

Assessment methods
Each student will have to make a presentation of a research article. The presentation should last approximately 25 minutes and count for the 80% of the final grade. The student is expected to (1) Explain how the presented paper contributes to existing literature (2) explain the methodology and results (3) discuss the strengths and weaknesses of the paper, and, if possible, give your recommendations for changes that would strengthen the paper. The remaining 20% is going to depend on participation in lectures.

Syllabus

  • G. Koop (2003) Bayesian Econometrics, John Wiley & Sons
  • S. Chib and E. Greenberg (1995) Understanding the 
Metropolis-Hastings algorithm, The American Statistician 49, 
pp. 327-335
  • S.J. Koopman, N. Shephard and J.A. Doornik (1999), 
Statistical Algorithms for models in State Space using SsfPack 
2.2, Econometrics Journal 2, pp. 113-166.
  • J. Durbin and S.J. Koopman (2000), Time Series Analysis by 
State Space Methods, Oxford University Press
  • S. An and F. Schorfheide (2007) Bayesian Analysis of DSGE Models, Econometric Reviews 36, pp. 113-172
  • P. N. Ireland (2004) A method for taking models to the data, Journal of Economic Dynamics & Control 28, pp. 1205–1226
  • B. T. McCallum (2002) Consistent Expectations, Rational Expectations, Multiple-Solution Indeterminacies, and Least-Squares Learnability, NBER Working Paper 9218
  • T. Mancini Griffoli (2008) DYNARE User Guide. An introduction to the solution & estimation of DSGE models
    http://www.dynare.org/documentation-and-support/user-guide/Dynare-UserGuide-WebBeta.pdf

Office hours
By appointment.