Date:
Location:
This Week's Speaker
Anton Strezhnev (UChicago), "A Guide to Dynamic Difference-in-Differences Regressions for Political Scientists"
Abstract
Difference-in-differences (DiD) designs for estimating causal effects have grown in popularity throughout political science. Many DiD papers present their central results through an "event study" plot - a visualization that combines estimated dynamic average treatment effects for multiple post-treatment time periods alongside placebo tests of the main identifying assumption: parallel trends. Despite their ubiquity, the methods used in practice for the creation of these plots are not standardized and in many cases the approaches adopted by researchers can result in misleading inferences about both the treatment effects and the placebo tests. Building on and synthesizing recent contributions in the econometric literature on differences-in-differences designs, this paper illustrates some common pitfalls through a replication of three recently published papers in major political science journals. We identify three notable problems related to the incorrect specification of the baseline comparison time, incorrect inclusion of "always-treated" units, and sensitivity to effect homogeneity assumptions. We help provide researchers with additional intuition for the problems that arise due to effect heterogeneity and for the "contamination bias" result of Sun and Abraham (2021) through a novel decomposition of the dynamic event study regression in the style of Goodman-Bacon (2021) that allows researchers to recover the weights placed on each 2x2 comparison used to construct the effect estimates and placebos. These weights allow researchers to gauge the sensitivity of each estimate to potential effect heterogeneity.
The Applied Statistics Workshop (Gov 3009) meets all academic year, Wednesdays, 12pm-1:30pm, in CGIS K354. This workshop is a forum for advanced graduate students, faculty, and visiting scholars to present and discuss methodological or empirical work in progress in an interdisciplinary setting. The workshop features a tour of Harvard's statistical innovations and applications with weekly stops in different fields and disciplines and includes occasional presentations by invited speakers.
More information is available at the Gov 3009 website: https://projects.iq.harvard.edu/applied.stats.workshop-gov3009
All interested Harvard affiliates are invited to attend.