Library Header Image
LSE Research Online LSE Library Services

Bootstrap inference of matching estimators for average treatment effects

Otsu, Taisuke and Rai, Yoshiyasu (2017) Bootstrap inference of matching estimators for average treatment effects. Journal of the American Statistical Association, 112 (50). 1720 - 1732. ISSN 0162-1459

Text - Accepted Version
Download (851kB) | Preview
Identification Number: 10.1080/01621459.2016.1231613


Abadie and Imbens (2008) showed that the naive bootstrap is not asymptotically valid for a matching estimator of the average treatment effect with a fixed number of matches. In this article, we propose asymptotically valid inference methods for matching estimators based on the weighted bootstrap. The key is to construct bootstrap counterparts by resampling based on certain linear forms of the estimators. Our weighted bootstrap is applicable for the matching estimators of both the average treatment effect and its counterpart for the treated population. Also, by incorporating a bias correction method in Abadie and Imbens (2011), our method can be asymptotically valid even for matching based on a vector of covariates. A simulation study indicates that the weighted bootstrap method is favorably comparable with the asymptotic normal approximation by Abadie and Imbens (2006). As an empirical illustration, we apply the proposed method to the National Supported Work data.

Item Type: Article
Official URL:
Additional Information: © 2017 Taylor & Francis
Divisions: Economics
Subjects: Q Science > QA Mathematics
Date Deposited: 05 Sep 2017 13:25
Last Modified: 29 May 2024 16:24
Projects: SES-0720961
Funders: European Research Council

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics