EconBase
← All papers

Two-way Fixed Effects and Differences-in-Differences Estimators with Several Treatments

Clément de Chaisemartin, Xavier D'Haultfœuille

arXiv 18 Dec 2020 · Econometrics · publishedJournal of Econometrics (2023) · 167 citations (OpenAlex)

arXiv:2012.10077 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We study two-way-fixed-effects regressions (TWFE) with several treatment variables. Under a parallel trends assumption, we show that the coefficient on each treatment identifies a weighted sum of that treatment's effect, with possibly negative weights, plus a weighted sum of the effects of the other treatments. Thus, those estimators are not robust to heterogeneous effects and may be contaminated by other treatments' effects. We further show that omitting a treatment from the regression can actually reduce the estimator's bias, unlike what would happen under constant treatment effects. We propose an alternative difference-in-differences estimator, robust to heterogeneous effects and immune to the contamination problem. In the application we consider, the TWFE regression identifies a highly non-convex combination of effects, with large contamination weights, and one of its coefficients significantly differs from our heterogeneity-robust estimator.

Citation extraction

30
references
102
in-text mentions
30
distinct cited
0
self-citations
15,171
main-text words

appendix boundary found by appendix_command · 54% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1V Joseph Hotz \ Mo Xiao (2011) The impact of regulations on the supply and quality of care in child care markets0.69391100%
2Kirill Borusyak \ Xavier Jaravel (2017) Revisiting event study designs0.69361100%
3Clement de Chaisemartin \ Xavier D'Haultfuille (2020) Two-way fixed effects estimators with heterogeneous treatment effects0.65431184%
4Liyang Sun \ Sarah Abraham (2021) Estimating dynamic treatment effects in event studies with heterogeneous treatment effects0.6069167%
5Andrew Goodman-Bacon (2021) Difference-in-differences with variation in treatment timing0.58531100%
6Marianne Bertrand, Esther Duflo \ Sendhil Mullainathan (2004) How much should we trust differences-in-differences estimates?0.51121100%
7James Robins (1986) A new approach to causal inference in mortality studies with a sustained exposure period-application to control of the healthy w…0.4052150%
8Alberto Abadie (2005) Semiparametric Difference-in-Differences Estimators0.40511100%
9Clément de Chaisemartin \ Xavier d'Haultfoeuille (2021) Two-way fixed effects regressions with several treatments0.40511100%
10Orley Ashenfelter (1978) Estimating the effect of training programs on earnings0.40511100%

Showing the top 10 of 30 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Contamination Bias in Linear Regressions0.89474
2Difference-in-Differences with Multiple Events0.64422
3Identification in Endogenous Sequential Treatment Regimes0.40511
4Inference with few treated units0.40511
5On the relationship between prediction intervals, tests of sharp nulls and inference on realized treatment effects in settings with few treated units0.40511