Overlap weight and propensity score residual for heterogeneous effects: A review with extensions
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, Jin-young | - |
dc.contributor.author | Lee, Myoung-jae | - |
dc.date.accessioned | 2022-12-08T10:41:47Z | - |
dc.date.available | 2022-12-08T10:41:47Z | - |
dc.date.created | 2022-12-08 | - |
dc.date.issued | 2023-01 | - |
dc.identifier.issn | 0378-3758 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/146467 | - |
dc.description.abstract | Individual responses to a treatment D = 0, 1 differ, depending on covariates X. Averaging such a heterogeneous effect is usually done with the density of X, but averaging with 'overlap weight (OW)' is also often done, where OW is the normalized version of PSx(1-PS) with PS denoting the propensity score. OW attains its maximum at PS = 0.5, i.e., when subjects in one group have the best overlap with the other group, and OW accords several advantages to treatment effect estimators as reviewed in this paper. First, matching with OW addresses the non-overlapping support problem in a built-in way, without an arbitrary user intervention. Second, inverse probability weighting with OW overcomes the "too small denominator problem ", and can be efficient as well. Third, regression adjustment with OW is robust to misspecified outcome regression models. Fourth, covariate balance holds exactly, if OW is estimated by the generalized method of moment. In these advantages, the PS residual 'D - PS' plays a central role. We also discuss some shortcomings of OW, and show how seemingly unrelated estimators are in fact closely related through OW. Finally, we provide an empirical illustration.(C) 2022 Elsevier B.V. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER | - |
dc.subject | DOUBLE ROBUSTNESS | - |
dc.subject | CAUSAL INFERENCE | - |
dc.subject | EFFICIENT | - |
dc.title | Overlap weight and propensity score residual for heterogeneous effects: A review with extensions | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Myoung-jae | - |
dc.identifier.doi | 10.1016/j.jspi.2022.04.003 | - |
dc.identifier.scopusid | 2-s2.0-85132214738 | - |
dc.identifier.wosid | 000814583400002 | - |
dc.identifier.bibliographicCitation | JOURNAL OF STATISTICAL PLANNING AND INFERENCE, v.222, pp.22 - 37 | - |
dc.relation.isPartOf | JOURNAL OF STATISTICAL PLANNING AND INFERENCE | - |
dc.citation.title | JOURNAL OF STATISTICAL PLANNING AND INFERENCE | - |
dc.citation.volume | 222 | - |
dc.citation.startPage | 22 | - |
dc.citation.endPage | 37 | - |
dc.type.rims | ART | - |
dc.type.docType | Review | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Mathematics | - |
dc.relation.journalWebOfScienceCategory | Statistics & Probability | - |
dc.subject.keywordPlus | DOUBLE ROBUSTNESS | - |
dc.subject.keywordPlus | CAUSAL INFERENCE | - |
dc.subject.keywordPlus | EFFICIENT | - |
dc.subject.keywordAuthor | Overlap weight | - |
dc.subject.keywordAuthor | Propensity score residual | - |
dc.subject.keywordAuthor | Matching | - |
dc.subject.keywordAuthor | Inverse probability weighting | - |
dc.subject.keywordAuthor | Regression adjustment | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.