Module 2500 in Hohenheim
Advanced Applied Econometrics 1:
Linear Models and Panel Data
Lecturers
Prof. Dr. Sebastian Hess, s.hess@uni-hohenheim.de
Prof. Dr. Silke Hüttel, silke.huettel@uni-goettingen.de
Prof. Dr. Christine Wieck, christine.wieck@uni-hohenheim.de
Prof. Dr. Stefan Hirsch, s.hirsch@uni-hohenheim.de
Aims
At the end of the course, students shall
- understand the basic econometric methods and be able to apply these to real problems,
- understand, apply and interpret theory-based econometric models,
- are able to handle cross section and panel data
- are able to work with the econometrics package R
Skills: Methodological competence, quantitative analysis, conceptual thinking
Contents
- Econometric methods: OLS, GLS, IV, GMM
- Static and dynamic models for panel data
- Mixed effects models
- Empirical problems
Outline
Textbook: Verbeek, M. (2012): A Guide to Modern Econometrics, 4th edition. John Wiley & Sons
relevant chapters/sections or alternative readings given in parentheses
- Refresher Ordinary Least Squares (OLS) (2.1-2.6; 5.1)
- The linear regression model
- The Ordinary Least Squares Estimator (OLSE)
- Properties of the OLSE (small sample and asymptotic properties)
- Goodness of fit and hypothesis testing
- Refresher Generalized Least Squares (GLS) (4.1-4.3; 4.6)
- Heteroskedasticity (introduction, implications for the estimator, testing, correction)
- Autocorrelation (introduction, implications for the estimator, testing)
- Panel Data I: Static Linear Models for Panel Data (10.1-10.3)
- Introduction to panel data
- Models, assumptions and estimation
- Testing
- Goodness of fit
- Two-way effects model
- Mixed Effects (Bates et al. 2015, Gardiner et al. 2009)
- Random intercepts and random slopes
- Nested effects versus crossed effects
- Model selection and estimation issues
- Endogenous Regressors and Instrumental Variables Estimation (IVE) (5.1-5.4)
- Review OLS properties and cases where OLS cannot be saved
- The IV- and GIV-Estimator
- Testing
- Control Function Approach
- Weak Instruments (Stock and Yogo 2002)
- Problem and detection of weak instruments
- Testing for overidentifying restrictions
- Panel Data II: Instrumental Variables (10.4)
- Panel data and endogenous regressors
- Hausman-Taylor approach under correlated effects
- Generalized Method of Moments (GMME) (5.5-5.6)
- The GMME
- Illustration
- Weak Identification
- Panel Data III: Dynamic Models for Panel Data (10.4-10.5; Bond 2002)
- Model and assumptions
- Estimation: Anderson-Hsiao, Arellano-Bond, Blundell-Bond System GMM
- Testing
| Teaching forms | Workload (h) |
|---|---|
| 1 week block seminar with lecture and exercise | 40 |
| Exercises | 50 |
| Total | 90 |
Examination: Exercises
Grading: In-class and homework assignments, where a minimum score of 50% is required to pass the module.
Credit points: 3 CP
Language: English
Literature
- Core textbook for this course:
Verbeek, M. (2012): A Guide to Modern Econometrics. John Wiley & Sons; 4th edition. - Bates, D., Maechler, M., Bolker, B., and S. Walker (2015). Fitting Linear Mixed-Effects Models Using lme4. Journal of Statistical Software, 67(1), 1-48. https://www.jstatsoft.org/article/view/v067i01/0
- Bond, S.R. (2002): Dynamic panel data models: a guide to micro data methods and practice. Portuguese Economic Journal 1: 141.
- Gardiner, J.C., Z., Luo, Z., and L.A. Roman (2009). Fixed effects, random effects and GEE: What are the differences? Statistics in Medicine 2009; 28:221–239.
- Stock, J. H., J. H. Wright, and M. Yogo (2002). A survey of weak instruments and weak identification in generalized method of moments, Journal of Business and Economic Statistics, 20, 518–29.
Software: R
During the course all exercises can be conducted in R or Stata, while support will be given in R only and our handouts will be in R. Therefore, please familiarize yourself with basics in R if R is new to you. We recommend working at least through the following introductory material:
http://www.r-tutor.com/r-introduction
https://cran.r-project.org/doc/contrib/Torfs+Brauer-Short-R-Intro.pdf