ECONOMETRICS: Standard Errors for Difference-in-Difference Regression; Professor Bruce E. Hansen (University of Wisconsin-Madison)

Abstract

This paper makes a case for the use of jackknife methods for standard error, p-value, and confidence interval construction for difference-in-difference regression. We review CRVE1, CRVE2, bootstrap, and jackknife standard error methods, and show that the first three can substantially underperform in conventional settings. In contrast, our proposed jackknife inference methods work well in broad contexts. We illustrate the relevance by replicating several influential DiD applications, and showing how inferential results can change if jackknife standard error and inference methods are used.

Click here to view paper.