312214 Praktische Übung "Labour Econometrics" (Ü) (SoSe 2022)

In the process of this course students will become familiar with a number of selected topics in labour economics and corresponding econometric methods. The course will consist of two parts. The first part will be conducted by Prof. Anna Zaharieva. This part will include the theory of human capital and returns to schooling, discrimination of minorities, the role of social networks for job search and intergenerational schooling mobility. In particular, the focus of this part will be on testing predictions from theoretical models by means of standard econometric techniques. In each of the four large topics emphasized above students will study the benchmark labour market model and analyze the set of corresponding model predictions. These theoretical hypotheses will then be confronted with the empirical data for Germany, which is a subset of variables from the German Socio-Economic Panel. Empirical analysis in the first part will follow the lines of standard econometric techniques, including a multivariate linear regression model, hypothesis testing, interaction terms, the Blinder-Oaxaca decomposition, binary response models (logit/probit) as well as ordered probit and multinomial logit specifications. The key indicators will be analyzed based on German labour market data and include returns to schooling and seniority for men and women, the gender wage gap, wage inequality as well as the effect of social contacts on wages and the probability of finding a job.

The second part of the course will be conducted by Dr. Michael Stops from the Institute for Employment Research (IAB, Nuremberg). The focus of this part will be on the specification and the estimation of models based on panel data. This part of the course will start with a discussion of the most important properties of panel data. Based on this, it will review the standard linear regression models and their application to panel data sets including pooled OLS, Fixed effects and Random effects models. In the end the course will also include dynamic models based on GMM and system GMM estimators (including the specification tests). Students will also learn how to practically implement all the estimators in Stata.