Data and Code for: Two-way fixed effects estimators with heterogeneous treatment effects

Principal Investigator(s):  View help for Principal Investigator(s) Clément de Chaisemartin, UC Santa Barbara; Xavier D'Haultfoeuille, CREST-ENSAE

Version:  View help for Version V2

Name File Type Size Last Modified
Enikolopov_et_al.do text/x-stata-syntax 2.8 KB 05/20/2020 06:56:AM
Gentzkow_et_al.do text/x-stata-syntax 7.5 KB 05/20/2020 12:24:AM
NTV_Aggregate_Data.dta application/x-stata 774.8 KB 03/20/2020 04:52:AM
Read me.pdf application/pdf 39.7 KB 05/20/2020 12:22:PM
WAGEPAN.DTA application/x-stata 220.1 KB 03/20/2020 04:52:AM
build_cond_expectation_1.ado text/plain 3.8 KB 05/20/2020 12:50:AM
build_cond_expectation_2.ado text/plain 4 KB 07/26/2018 05:02:PM
code_unions.do text/x-stata-syntax 7.4 KB 06/08/2020 10:27:AM
createYvalues.mo application/octet-stream 2.6 KB 07/26/2018 05:05:PM
did_multiplegt.ado text/plain 40.9 KB 05/19/2020 11:36:PM

Project Citation: 

de Chaisemartin, Clément, and D’Haultfoeuille, Xavier. Data and Code for: Two-way fixed effects estimators with heterogeneous treatment effects. Nashville, TN: American Economic Association [publisher], 2020. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2020-08-26. https://doi.org/10.3886/E118363V2

Project Description

Summary:  View help for Summary Linear regressions with period and group fixed effects are widely used to estimate treatment effects. We show that they estimate weighted sums of the average treatment effects (ATE) in each group and period, with weights that may be negative. Due to the negative weights, the linear regression coefficient may for instance be negative while all the ATEs are positive. We propose another estimator that solves this issue. In the two applications we revisit, it is significantly different from the linear regression estimator.

Scope of Project

Subject Terms:  View help for Subject Terms linear regressions; fixed effects; heterogeneous treatment effects; difference-in-differences
JEL Classification:  View help for JEL Classification
      C21 Single Equation Models; Single Variables: Cross-Sectional Models; Spatial Models; Treatment Effect Models; Quantile Regressions
      C23 Single Equation Models; Single Variables: Panel Data Models; Spatio-temporal Models
Geographic Coverage:  View help for Geographic Coverage United States and Russia
Time Period(s):  View help for Time Period(s) 1868 – 1999 (1868-1928 in Section 5.B, 1980-1987 in Section 5.C, 1995-1999 in Section 2.2 of the appendix.)
Data Type(s):  View help for Data Type(s) administrative records data; survey data


Related Publications

Download this project

Published Versions

V2 [2020-08-26]

Export Metadata

Dublin Core

DDI 2.5

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as received from the data depositor. As of April 2026, depositors are required to submit study materials in accessible formats. ICPSR has not reviewed, checked, or processed this material. For additional information about the study, please contact the investigator(s) directly. If you have questions about the accessibility of materials distributed by ICPSR or require further assistance, please visit ICPSR's Accessibility Center.