GESIS Training Courses

Scientific Coordination

Sebastian E. Wenz
Tel: +49 221 47694-159

Administrative Coordination

Loretta Langendörfer M.A.
Tel: +49 221 47694-143

Recent Developments in Difference-in-Differences Estimation

Cologne / Unter Sachsenhausen 6-8
General Topics:
Course Level:
Software used:
Students: 550 €
Academics: 825 €
Commercial: 1650 €
Additional links
Lecturer(s): Scott Cunningham

About the lecturer - Scott Cunningham

Course description

When researchers are not able to field randomized experiments to study the causal effects of large social programs due to their size, associated costs, feasibility, and ethical constraints, they often rely on natural experiments such as law changes or natural disasters.  The most popular research design for estimating the causal effects using longitudinal data is the difference-in-differences design. The method is extremely popular in the empirical social sciences.  For instance, around 25% of all papers at the NBER working paper series use difference-in-differences.
But, while difference-in-differences is relatively straightforward, unbiasedness in the parameter estimates depends on the setup of the quasi-experiment and the methodology used. For instance, when there are more than one dates when units are treated, then traditional panel methods are no longer guaranteed to be unbiased, even under parallel trends. Our understanding of these issues has evolved considerably over the last several years, both in terms of econometric theory and software implementation. This course will review this emerging work covering both the intuition behind the statistical models and the technical details of the models themselves using lectures, discussion and group exercises using R and/or Stata.
On the last day, we will review the synthetic control estimator which will be presented as an option for when the conditions that make difference-in-differences not ideal are more suitable for this method.
Please note: There is a trade fair in Cologne during this week. We recommend that you book your hotel accommodation as soon as possible.
For additional details on the course and a day-to-day schedule, please download the full-length syllabus.

Target group

Participants will find the course useful if:
  • They work on policy analysis in either public policy or private policy (e.g., industry)
  • They are academics who work on problems needing estimates of causal inference
  • They are students wishing to learn these methods for a thesis or dissertation

  • Learning objectives

    By the end of the course participants will:
  • Be able to apply the methods covered in class in their own research using software such as R or Stata.  
    Organizational structure of the course
    Days will be spent mixing lecture, discussion, and labs exercises.  We have 15 min breaks on the hour, 1 hour break for lunch, and then continue with the same rhythm until end of day.  


    Econometrics preferred, another causal inference course preferred, exposure to potential outcomes model, but we will be focused on beginner to advanced, so if not it's not a problem.
    Software and hardware requirements
    Course participants will need to bring a laptop with R/RStudio and Stata installed. The latest versions of R and RStudio are available for free at and Participants may receive a Stata short term license provided by GESIS for the duration of the course if needed.
    Participants will need to be able to download files from the internet (free Wifi is provided by GESIS) and have the rights to install R packages or Stata Ados on their laptops during the course.

    Recommended readings