From 2 November 2020, the autumn semester 2020 will take place online. Exceptions: Courses that can only be carried out with on-site presence. Please note the information provided by the lecturers via e-mail.
This course introduces students to key statistical methods for analyzing social science data with a special emphasis on causal inference and policy evaluation.
Students - have a sound understanding of standard regression techniques - know strategies to test causal hypotheses using regression analysis and/or experimental methods - are able to formulate and implement a regression model for a particular policy question and a particular type of data - are able to critically interpret results of applied statistics, in particular, regarding causal inference - are able to critically read and assess published studies on policy evaluation - are able to use the statistical software Stata for data analysis
The topics covered in the first part of the course are a revision and linear regression and non-linear regression techniques such as probit and logit regression analysis. The second part of the course focuses on causal inference and introduces methods such as panel data analysis, difference-in-difference methods, instrumental variable estimation, regression discontinuity design, and randomized controlled trials used for policy evaluation. The course shows how the various methods differ in terms of the required identifying assumptions to infer causality as well as the data needs.
Students will apply the methods from the lectures by solving bi-weekly assignments using statistical software and data sets provided by the instructors. These data sets will cover topics at the interface of policy, technology and society. Solving the assignments contributes to the final grade with a weight of 30%.
Performance assessment information (valid until the course unit is held again)