The Difference-in-Differences (DiD) method is a powerful quasi-experimental research design widely used for estimating causal effects in policy research. In recent years, a growing body of literature has highlighted important limitations of traditional DiD approaches and proposed solutions to address them.
This talk aims to equip social policy researchers with up-to-date tools for implementing DiD designs effectively and credibly in real-world applications. It will begin with a review of the basic 2×2 DiD design and its generalized form, the Two-Way Fixed Effects (TWFE) model. The talk will then demonstrate how TWFE estimators can produce biased results when treatment effects are heterogeneous—that is, when they vary across groups or over time. To address these challenges, the presentation will introduce heterogeneity-robust DiD estimators developed in recent years, including those proposed by Callaway and Sant’Anna (2021) and Borusyak, Jaravel, and Spiess (2024). The final section will cover additional concerns relevant to applied researchers, such as testing for parallel trends and incorporating covariates.
Booking is required for people outside of the Department of Social Policy and Intervention (DSPI).
DSPI Members do not need to register.