How Much Should We Trust Staggered Difference-in-Differences Estimates? 

Charles Wang,
Glenn and Mary Jane Creamer Associate Professor of Business Administration, Harvard Business School
Difference-in-differences (DiD) analysis with staggered treatment timing is frequently used to assess the impact of policy changes on corporate outcomes in finance research. This talk reviews the nascent literature in econometrics examining the properties of staggered DiD estimators, explains how and when biases can arise, and provides some suggestions for causal inference using these settings as well as strands of the literature worth re-examining.