Econometric Analysis of Panel Data

Spring 2009, 4:40-6:30pm TTH (CH296)
Prof. K.-P. Lin (CH 241G, 725-3931)
Office Hours: 3:30-4:30 TTH & by appointment

This is a course on applied econometrics dealing with ‘panel’ or ‘longitudinal’ data sets. Topics to be studied include specification, estimation, and inference in the context of models that include individual (firm, person, etc.) and/or time effects. We will begin with a development of the standard linear regression model, then apply it to panel data settings involving ‘fixed’ and ‘random’ effects. The basic model will be extended to dynamic models with recently developed GMM and instrumental variables methods. We will consider numerous applications from the literature, including static and dynamic panel data regression models.

Basic understanding of econometric analysis is required (EC 370, 570 or equivalent). Knowledge of calculus, algebra, probability theory and statistics are essential for this course. Familiar with computer programming and econometric packages will be useful. Stata 10 will be used throughout the course.

 

Texts and Software

• Required:
  • W. H. Greene, Econometric Analysis, 6th ed., Chapter 9: Models for Panel Data (and selected sections in Chapters 12 and 15), Prentice Hall, 2008.
  • A. Colin Cameron and Pravin K. Trivedi, Microecometrics: Methods and Applications, Part V, Models for Panel Data, Cambridge University Press, 2005.
  • Stata 10, StataCorp, 2008. A version of Small Stata may be used for the class.
• Recommended:
  1. M. Arellano, Panel Data Econometrics, Oxford University Press, 2003.
  2. B. H. Baltagi, Econometric Analysis of Panel Data, 3rd ed., John Wiley, New York, 2005.
  3. C. Hsiao, Analysis of Panel Data, 2nd ed., Cambridge University Press, 2003.
  4. J. M. Wooldridge, Econometric Analysis of Cross Section and Panel Data, The MIP Press, 2002.
  5. A. Colin Cameron and Pravin K. Trivedi, Microeconometrics Using Stata, Stata Press, 2009.

Topics

1. Reviews of Basic Econometrics
   1. Simple and Multiple Regression
   2. System of Regression Equations
   3. Model Estimation: OLS, IV, 2SLS, 3SLS
   4. Hypothesis Testing and Inference
2. Linear Panel Data Analysis: Basic
   1. Pooled Model
   2. Fixed Effects Model
   3. Random Effects Model
   4. First-Difference Model
3. Linear Panel Data Analysis: Extensions
   1. Heteroscedasticity and Autocorrelation
   2. Instrumental Variable and GMM Estimation
4. Time Series Panel Data
   1. Time Series Correlation in Panel Data
   2. Dynamic Panel Data Analysis
5. Spatial Panel Data
   1. Spatial Correlation in Panel Data
   2. Panel Spatial Econometric Models
6. Advanced Topics (Time Permitting)
   1. Nonlinear Panel Data: Probit, Logit, Tobit Models
   2. Time-Space Autoregressive and Moving Average

Lecture Notes

1, 2, 3, 4, 5, 6, 7, 8, 9, 10, …

Case Study and Homework

Expectation

1. There will be a mid-term (May 7, in class) and a final exam (June 9, 5:30pm). In addition, 3 or 4 homeworks will be assigned periodically (due every 2 weeks in average).
2. A course project is required for graduate students taking this course EC510. The project must be a panel data econometric model. A one-page project proposal is due on or before May 21 for approval. Final report of the project is then due on or before June 9.
3. Grade distribution of this course looks like this:
   

   	EC410	EC510
   Mid-Term	40%	30%
   Final	40%	30%
   Project		20%
   Homeworks	20%	20%