Econometric Methods II

PhD Course, Economics Department, Universitat Pompeu Fabra and Barcelona GSE, 2011

Fridays 9am-11am (20.173) and 5pm-7pm (20.031)
TA sessions: Thursdays 9.00-10.00, (20.029)
Office Hours: Thursdays 11.30am-13.00am, Room 23.408
Exam date: June 20 11am - 1pm , 13.007


Overview

This course aims at equipping students with the tools needed to produce applied macro economic research. Most of the material can be found in "Time Series Analysis" by James D. Hamilton (Princeton University Press, 1994) and Cochrane's text, but reading articles will also be required.


Syllabus

Lecture 1 Overview and introduction
Hamilton Appendix A4

Lecture 2 Linear Difference Equations
Hamilton Ch. 1-2

Notes and MatLab code for TA Session 1 (April 19)

Lecture 2 Stationary ARMA models
Hamilton Ch. 3

Lecture 4 Forecasting and prediction
Hamilton Ch.4.1-4.3 and Cochrane Ch. 5 - 6
Notes on the Projection Theorem

Homework 1 (due 24.00 Monday April 30)

Lecture 5 Maximum Likelihood Estimation
Hamilton Ch.5
Slides on Numerical Maximization

Lecture 6 Estimating Vector Autoregressions (VARs)
Hamilton Ch.8.1, 10.1, 11.1 and Lutkepohl Ch 4.1, 4.2, 4.3, 4.6
Slides on choosing lag order

Notes and MatLab code for TA Session 2 (May 3)

Lecture 7 Structural VARs: Identification
Hamilton Ch 11.4 -11.6, Cochrane Ch 7.1-7.2 and Leeper, Sims and Zha (1996)

Lecture 8 Identification of Structural VARs II
Cochrane Ch 7.1-7.2
Blanchard and Quah (1989)
Rudebusch (1998)
Sims(1996!) response to Rudebusch (1998)
Gali(1999) Chari, Kehoe and McGrattan (2008) Ellen McGrattan in multimedia format
Slides

Lecture 9 Factor models
Stock and Watson (2010) and Bernanke, Boivin and Eliasz (2005)
Slides and MatLab code

Homework 2 (due 24.00 Sunday May 20)

Lecture 10 - 11 Cointegration
Hamilton Ch 19.1 - 19.2 and Cochrane Ch 11

MatLab code for TA Session 3 (May 17)

Lecture 12 State space models and the Kalman filter
Hamilton Ch 13
Lecture notes on the Kalman Filter

Lecture 13 Applications of the Kalman filter
Hamilton Ch 13
Slides
MatLab code

Lecture 14 ML Estimation of State Space Models
Hamilton Ch 5
Slides
Goffe et al (1994)
Duffee (2011)
MatLab code

Notes and MatLab code for TA Session 4 (May 31)

Lecture 15 Conditional Heteroscedasticity
Hamilton Ch 21
Robert Engle's 2003 Nobel Lecture

Lecture 16 Introduction to Bayesian Statistics
Slides
Eddy (2004)

Homework 3 (due 24.00 Tuesday June 12)

Lecture 17 The Metropolis-Hasting Algorithm
Chib (2001)
An and Schorfheide (2007)
Slides and MatLab Code used for slides

Lecture 18 Bayesian Posterior Analysis and the Gibbs sampler
Chib (2001)
Slides

MatLab code for TA Session 5 (June 14)

Homework 4 (due 24.00 Sunday July 1)

Lecture 19 - 20 Course Review

Exercise Questions for exam