Microcredential ekomex Differences-in Differences Methods

Master causal inference with observational panel data in this three-day course that equips you with modern Differences-in-Differences techniques and advanced estimators for complex real-world scenarios through hands-on examples from across the social sciences.

What Is This Course About?
This three-day in-person course provides you with the skills needed to make causal inference claims using observational panel data in the context of your research field. The course covers the canonical Differences-in-Differences framework, as well as estimators that provide valid inference in the presence of heterogeneous treatment effects and violations of the parallel trends assumption. In the course, we will cover empirical examples from different fields within the empirical social sciences and discuss some common implementation issues. You will also have the opportunity to discuss issues in your own work and get feedback on the empirical implementation.

Learning Goals

• Be able to implement different DiD-estimators for your empirical research question.
• Learn about the necessary assumptions for valid inference and assess the suitability of different DiD-estimators in different empirical circumstances.
• Be aware of common implementation pitfalls when using DiD estimators.

Recommended Readings for the Course

• De Chaisemartin, C. and D’Haultfœuille, X., 2023. Credible answers to hard questions: Differences-in-differences for natural experiments. Available at SSRN.
• Janys, L. and Siflinger, B., 2024. Mental health and abortions among young women: Time-varying unobserved heterogeneity, health behaviors, and risky decisions. Journal of Econometrics, 238(1), p.105580.
• De Chaisemartin, C. and d’Haultfœuille, X., 2020. Two-way fixed effects estimators with heterogeneous treatment effects. American economic review, 110(9), pp.2964-2996.

Assignments for the Course
Two assignments (not graded) with both an theoretical and an empirical component.

Schedule

• Day 1
  90’ synchronous lecture: Introduction to notation, canonical did framework
  90’ synchronous lab using simulated data and empirical examples
  60’ independent work on empirical example
  60’ office hours and Q&A for assignments.
• Day 2
  90’ synchronous lecture: Heterogeneous treatment effects in the did-framework with staggered-treatment timing
  90’ synchronous lab using simulated data and empirical examples
  60’ independent work on empirical example
  60’ office hours and feedback for assignments from Day 1.
• Day 3
  90’ synchronous lecture: violations of the parallel trends assumption: synthetic control and grouped fixed effects.
  90’ synchronous lab using simulated data and empirical examples
  60’ independent work on empirical example
  60’ office hours and feedback for assignments from Day 2.

In addition, students should plan for sufficient time to do the assigned daily homework and read the assigned literature in advance. The course does not require any advanced prior knowledge in R. However, for students with no prior experience with R, we recommend either the short course “Introduction to R” or we will post a link to some online materials to familiarise themselves with the language in advance.

Who Is Your Instructor?
Lena Janys is a full professor for Econometrics at the Department of Economics at the University of Konstanz who specializes in microeconometrics, with an emphasis on panel data methods for causal inference and applications in both Health- and Labor Economics. She has published in prestigious international journals such as the Review of Economics and Statistics and the Journal of Econometrics.
https://sites.google.com/site/janyslena/home
@lenajanys.bsky.social