Causal forests with fixed effects for treatment effect heterogeneity in difference-in-differences

Mark Kattenberg (), Bas Scheer () and Jurre Thiel ()
Additional contact information
Mark Kattenberg: CPB Netherlands Bureau for Economic Policy Analysis
Bas Scheer: CPB Netherlands Bureau for Economic Policy Analysis
Jurre Thiel: CPB Netherlands Bureau for Economic Policy Analysis

No 452, CPB Discussion Paper from CPB Netherlands Bureau for Economic Policy Analysis

Abstract: Recently developed heterogeneity-robust two-way fixed effects (TWFE) estimators do not quantify the full heterogeneity in treatment effects in a difference-in-differences research design. We therefore present a computationally feasible algorithm to estimate heterogeneous treatment effects in the presence of many fixed effects using causal forests. Our modification identifies treatment effects by partialling out fixed effect using group averages. Simulation results suggest that our algorithm provides consistent estimates of the Conditional Average Treatment effect for the Treated in a (staggered) difference-in-differences research design. Finally, we use our method to document heterogeneity in the treatment effect of alternative work arrangements (payrolling) on hourly wages. We find evidence that wages fell by 3.7 percent in the first year of payrolling for a specific subgroup of workers only. Both conclusions did not appear in a conventional heterogeneity analysis using manual subgroups. The R-code of our algorithm is publicly available online.

JEL-codes: C18 C23 C88 (search for similar items in EconPapers)
Date: 2023-11
New Economics Papers: this item is included in nep-ecm
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.cpb.nl/sites/default/files/omnidownloa ... e-in-differences.pdf (application/pdf)

Related works:
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:cpb:discus:452

DOI: 10.34932/216c-yz58

Access Statistics for this paper

More papers in CPB Discussion Paper from CPB Netherlands Bureau for Economic Policy Analysis Contact information at EDIRC.
Bibliographic data for series maintained by ().