• MLU Halle-Wittenberg – Löwengebäude
  • Ifo Institut Dresden
  • Universität Leipzig -Treppenhaus Albertina
  • Universität Leipzig – Institutsgebäude
  • TU Dresden – Luftbild
  • Universität Madgeburg
  • IWH – Außenansicht
  • Universität Leipzig – Leibniz-Denkmal
  • TU Dresden – Vorderansicht
  • TU Dresden – Hörsaalzentrum auf dem Campus
  • IWH Innenhof
  • FSU – Vorderansicht
  • FSU – von oben
  • FSU – Saal
  • OvGU Gelände

Causal Inference for Economists

Lecturer: Professor Benjamin Elsner, PhD (University College Dublin)
Date: May 21-24, 2024
Venue: TU Dresden, Faculty of Business and Economics, Münchner Platz 3, 01187 Dresden, room SCH B 37
Registration: until May 10, 2024 via email: yvonne.bludau@tu-dresden.de.

Announcement and List of References: pdf

Required Activities
Theory and short presentations

Overview and Objectives
This course introduces students to the most important causal research designs in economics. We begin with directed acyclic graphs (DAGs) as a systematic framework for thinking about causality and uncovering common pitfalls in causal research designs. The main part of the course covers canonical research designs that are common in many fields of economics: selection on observables, instrumental variables, regression discontinuity and difference-in-differences and delves into more recent developments such as staggered adoption designs, regression kink designs or (time permitting) bunching. For each technique, we will discuss theory and applications. Students are expected do short group presentations of recent papers using causal research designs. I will also provide R codes that allows students to perform their own analyses. Advice for Stata can be provided upon request.

Tuesday, May 21, 2024
9:00-10:30, 11:00-12:30, 13:30-15:00

Wednesday, May 22, 2024
9:00-10:30, 11:00-12:30, 13:30-15:00

Thursday, May 23, 2024
9:00-10:30, 11:00-12:30, 13:30-15:00

Friday, May 24, 2024
9:00-10:30, 11:00-12:30, 13:30-15:00

Participants should be familiar with basic concepts of statistics and econometrics, especially linear regression and hypothesis testing.

Course Outline
1. Foundations of Causal Inference (DAGs)
2. Randomised Experiments and Potential Outcomes
3. Selection on Observables (Regression, Matching)
4. Instrumental Variables (Basics, Shift-share, Judge IV)
5. Regression Discontinuity and Kink Designs
6. Difference-in-Differences, Event Studies and Synthetic Controls
7. Advanced topics (time permitting)
a) Bunching designs
b) Marginal Treatment Effects
c) Bounding