Gaussian and Bootstrap Approximation for Matching-based Average Treatment Effect Estimators

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shi, Zhaoyang, Bhattacharjee, Chinmoy, Balasubramanian, Krishnakumar, Polonik, Wolfgang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913624484741120
author Shi, Zhaoyang
Bhattacharjee, Chinmoy
Balasubramanian, Krishnakumar
Polonik, Wolfgang
author_facet Shi, Zhaoyang
Bhattacharjee, Chinmoy
Balasubramanian, Krishnakumar
Polonik, Wolfgang
contents We establish Gaussian approximation bounds for covariate and rank-matching-based Average Treatment Effect (ATE) estimators. By analyzing these estimators through the lens of stabilization theory, we employ the Malliavin-Stein method to derive our results. Our bounds precisely quantify the impact of key problem parameters, including the number of matches and treatment balance, on the accuracy of the Gaussian approximation. Additionally, we develop multiplier bootstrap procedures to estimate the limiting distribution in a fully data-driven manner, and we leverage the derived Gaussian approximation results to further obtain bootstrap approximation bounds. Our work not only introduces a novel theoretical framework for commonly used ATE estimators, but also provides data-driven methods for constructing non-asymptotically valid confidence intervals.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17181
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gaussian and Bootstrap Approximation for Matching-based Average Treatment Effect Estimators
Shi, Zhaoyang
Bhattacharjee, Chinmoy
Balasubramanian, Krishnakumar
Polonik, Wolfgang
Statistics Theory
Econometrics
Probability
Machine Learning
We establish Gaussian approximation bounds for covariate and rank-matching-based Average Treatment Effect (ATE) estimators. By analyzing these estimators through the lens of stabilization theory, we employ the Malliavin-Stein method to derive our results. Our bounds precisely quantify the impact of key problem parameters, including the number of matches and treatment balance, on the accuracy of the Gaussian approximation. Additionally, we develop multiplier bootstrap procedures to estimate the limiting distribution in a fully data-driven manner, and we leverage the derived Gaussian approximation results to further obtain bootstrap approximation bounds. Our work not only introduces a novel theoretical framework for commonly used ATE estimators, but also provides data-driven methods for constructing non-asymptotically valid confidence intervals.
title Gaussian and Bootstrap Approximation for Matching-based Average Treatment Effect Estimators
topic Statistics Theory
Econometrics
Probability
Machine Learning
url https://arxiv.org/abs/2412.17181