The objective of this course is to deal with some important topics in the empirical analysis of micro data (households, firms). We will study issues in the specification, estimation and testing of different models. The emphasis of the course is both on the econometric techniques and in the economic applications. Development of programming skills in Stata will be an essential part of the course. The course is divided in the following major topics:
1. Instrumental Variables Estimation: Two-stage least squares. Testing and endogenous variables.
2. Pool of cross sections: Chow test. Policy evaluation using difference-in-differences estimator.
3. Linear Models for Panel Data: Static models and control for unobserved heterogeneity. First differences, within-groups, between-groups and GLS estimators. Specification tests. Dynamic models. Andserson-Hsiao and Arellano-Bond estiamtors.
4. Discrete Choice Models: Binary choice models for cross sectional data: linear probability models, probit and logit models. Interpretation. Maximum likelihood estimation. Multiple choice models: multinomial probit and multinomial logit.
5. Sample Selection Models: The Tobit model for corner solution responses. Censored and Truncated Regression models. Sample selection corrections.