Rematching Estimators for Average Treatment Effects
Abstract
Matching estimators are widely applied in practice for their great intuitive appeal. However, simple matching estimators with a fixed number of matches (M0) are generally inefficient. In this article, we propose matching estimators with a variable number of matches to gain efficiency via rematching. Rather than increasing M0 to gain precision, which introduces an increase in bias, the key is to rematch the treated units from the opposite direction to utilize unmatched control units. Our rematching estimators are applicable to both the average treatment effect and its counterpart for the treated population. The proposed rematching estimators are proven asymptotically valid and uniformly more efficient than matching estimators with the same M0. Simulation results confirm that the proposed rematching estimators substantially improve the simple matching estimators in finite samples. As an empirical illustration, we apply the estimators proposed in this article to the National Supported Work data.
Related
- Doubly robust augmented weighting estimators for the analysis of externally controlled single-arm trials and unanchored indirect treatment comparisons
- Finite-population inference for cross-fitted estimators of treatment contrasts in stratified multistage surveys
- Rank-based Model Average Estimator for Average Treatment Effects
- Differentially Private Average Treatment Effect Estimation by Propensity Score Blocking
- Estimating Average Treatment Effects with Projected Instrumental Variables
BibTeX
@misc{hui2026rematching,
title = {{Rematching Estimators for Average Treatment Effects}},
author = {Lam Lam Hui and Kin Wai Chan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.30560},
eprint = {2610.30560},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.30560},
}
RIS
TY - UNPB
TI - Rematching Estimators for Average Treatment Effects
AU - Lam Lam Hui
AU - Kin Wai Chan
PY - 2026
DA - 2026/10/22
PB - arXiv
DO - 10.48550/arxiv.2610.30560
UR - https://arxiv.org/abs/2610.30560
AB - Matching estimators are widely applied in practice for their great intuitive appeal. However, simple matching estimators with a fixed number of matches (M_0) are generally inefficient. In this article, we propose matching estimators with a variable number of matches to gain efficiency via rematching. Rather than increasing M_0 to gain precision, which introduces an increase in bias, the key is to rematch the treated units from the opposite direction to utilize unmatched control units. Our rematching estimators are applicable to both the average treatment effect and its counterpart for the treated population. The proposed rematching estimators are proven asymptotically valid and uniformly more efficient than matching estimators with the same M_0. Simulation results confirm that the proposed rematching estimators substantially improve the simple matching estimators in finite samples. As an empirical illustration, we apply the estimators proposed in this article to the National Supported Work data.
ER -