Full Citation

Title: Inference in Differences-in-Differences with Few Treated Groups and Heteroskedasticity

Citation Type: Journal Article

Publication Year: 2019

ISBN:

ISSN:

DOI: 10.1162/rest_a_00759

NSFID:

PMCID:

PMID:

Abstract: We derive an inference method that works in differences-in-differences settings with few treated and many control groups in the presence of heteroskedasticity. As a leading example, we provide theoretical justification and empirical evidence that heteroskedasticity generated by variation in group sizes can invalidate existing inference methods, even in data sets with a large number of observations per group. In contrast, our inference method remains valid in this case. Our test can also be combined with feasible generalized least squares, providing a safeguard against misspecification of the serial correlation.

Url: https://www.mitpressjournals.org/doi/abs/10.1162/rest_a_00759

User Submitted?: No

Authors: Ferman, Bruno; Pinto, Cristine

Periodical (Full): The Review of Economics and Statistics

Issue: 3

Volume: 101

Pages: 452-467

Data Collections: IPUMS USA

Topics: Other

Countries: