Contamination Bias in Linear Regressions

Paul Goldsmith-Pinkham, Peter Hull and Michal Koles\'ar

Papers from arXiv.org

Abstract: We study regressions with multiple treatments and a set of controls that is flexible enough to purge omitted variable bias. We show that these regressions generally fail to estimate convex averages of heterogeneous treatment effects -- instead, estimates of each treatment's effect are contaminated by non-convex averages of the effects of other treatments. We discuss three estimation approaches that avoid such contamination bias, including the targeting of easiest-to-estimate weighted average effects. A re-analysis of nine empirical applications finds economically and statistically meaningful contamination bias in observational studies; contamination bias in experimental studies is more limited due to smaller variability in propensity scores.

Date: 2021-06, Revised 2024-06
New Economics Papers: this item is included in nep-ecm
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (28)

Published in American Economic Review, Volume 114 Issue 12, December 2024, pages 4015-51

Downloads: (external link)
http://arxiv.org/pdf/2106.05024 Latest version (application/pdf)

Related works:
Journal Article: Contamination Bias in Linear Regressions (2024)
Working Paper: Contamination Bias in Linear Regressions (2022)
Working Paper: Contamination Bias in Linear Regressions (2022)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2106.05024

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().