Seminar on Treatment Effects: Estimation and Inference (master)
Kick-off Meeting: April 16, 2024, 9am - 12pm, Room 144, Ludwigstr. 33/I
Final presentation: July 11, 2024, 8:30am - 6:00 pm, Room 144, Ludwigstr. 33/I
Term paper submission: August 31, 2024
Tutors: Mauricio Olivares (m.olivares@lmu.de), Tomasz Olma (t.olma@lmu.de)
Teaching content: Treatment effects are the central object of interest in the econometrics of program evaluation. In this seminar, we will cover a series of recent developments in the theory and practice of estimation and inference on treatment effects based on experimental as well as observational data.
The seminar has two focal points. First, we will discuss the general methodology that sparked the use of modern machine learning methods in causal inference (orthogonal moments, cross-fitting). Several applications to relevant economic problems will be presented.
The second focal point is on practical and reliable inference methods for treatment effects. In particular, we will place special attention on techniques that do not rely on strong and sometimes unverifiable assumptions, namely bootstrap and randomization tests. We will showcase their potential for contemporary problems in Econometrics, such as the design and analysis of experiments, multiple testing, and multivariate inference.
Requisites: Intermediate Econometrics and Probability and Statistics at advanced undergraduate level. Recommended courses: Causal Inference (Wilhelm) Econometric Theory (Olivares) (add links to both courses)
Audience: PhD and Master students in statistics and economics
Evaluation: 11.07.2024
ECTS credits: After the kick-off meeting, students choose a paper, then present the paper at the end of the semester. For 3 ECTS this suffices. Students can also register for 9 ECTS, but then also need to write a term paper, to be submitted after the presentation. To acquire 12 ECTS credits students from the Master of Science in Economics have to write a term paper and have a presentation; the 3 ECTS- and 9 ECTS-option is not open to them.