|
Generalized Method of Moments - Theory and Practice
Instructor: Alastair Hall, North Carolina State University and University of Manchester
Dates: May 14-18, 2007
Location: American University
Objectives and Scope
Generalized Method of Moments (GMM) was first introduced into the econometrics literature in 1982 by Lars Hansen. Since then it has been widely applied to analyze economic and financial data. This interest has both stimulated and been facilitated by the development of numerous statistical inference techniques based on GMM estimators. These applications have been in very diverse areas spanning macroeconomics, finance, agricultural economics, environmental economics and labor economics. Depending on the context, GMM has been applied to time series, cross-sectional and panel data.
This course provides an introduction to estimation and inference within the GMM framework. The main focus is placed on GMM estimation in the context of time series data and the various inference procedures are illustrated using examples from agricultural economics, macroeconomics and finance.
The lectures and discussion are based on:
Hall, A. R., (2004), Generalized Method of Moments, Oxford University Press.
Content and topics
1. Introduction- Why GMM?- Statistical antecedents – Method of Moments, Minimum Chi-Square, Instrumental Variables - The instrumental variables estimator in the static linear regression model
2. Estimation in correctly specified nonlinear dynamic models- The population moment condition and identification- Estimation – identifying and overidentifying restrictions - Symptotic properties of the estimator - Long run variance estimation
3. Estimation in correctly specified models (continued)- Two-step and iterated estimation- The impact of normalizations - Continuous updating GMM estimator
4. Hypothesis testing- Overidentifying restrictions test- Testing subsets of moment conditions - Testing restrictions on the parameter - Testing structural stability
5. Finite sample behavior and moment selection- Review of evidence on finite sample behavior- Optimal choice of moments - Methods of moment selection
6. Weak identification and many instrument asymptotics
- Nature of weak identification
- Inference in the presence of weak identification
- Many instrument asymptotics
Matterials
The course will use the text Generalized Method of Moments (Oxford, 2006), written by the instructor. Students should purchase a copy of this text before the course begins.
To Order Book use link below or any other source/bookstore:
Ordering information: http://www.oup.com/us/catalog/general/subject/Economics/MacroeconomicTheory/?view=usa&ci=9780198775201
Location
American University, Washington, D.C.
Registration
Download the necessary document/s from the main
page and submit to the Economics department, or look at: http://www.american.edu/american/registrar/
About the instructorAlastair Hall is a professor in the Department of Economics at North Carolina State University. His most recent book is on GMM. He has published a large number of articles on GMM and related topics in the top econometrics and statistics journals. He is currently serving on the editorial boards of Econometric Reviews and Journal of Financial Econometrics, and served as co-editor of Journal of Business and Economic Statistics from 2001-2003.
|
