A Framework for Optimal Matching for Causal Inference

被引:0
|
作者
Kallus, Nathan [1 ,2 ]
机构
[1] Cornell Univ, Ithaca, NY 14853 USA
[2] Cornell Tech, New York, NY 10044 USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a novel framework for matching estimators for causal effect from observational data that is based on minimizing the dual norm of estimation error when expressed as an operator. We show that many popular matching estimators can be expressed as optimal in this framework, including nearest-neighbor matching, coarsened exact matching, and mean-matched sampling. This reveals their motivation and aptness as structural priors formulated by embedding the effect in a particular functional space. This also gives rise to a range of new, kernel-based matching estimators that arise when one embeds the effect in a reproducing kernel Hilbert space. Depending on the case, these estimators can be found using either quadratic optimization or integer optimization. We show that estimators based on universal kernels are universally consistent without model specification. In empirical results using both synthetic and real data, the new, kernel-based estimators outperform all standard causal estimators in estimation error.
引用
收藏
页码:372 / 381
页数:10
相关论文
共 50 条
  • [2] A matching framework to improve causal inference in interrupted time-series analysis
    Linden, Ariel
    [J]. JOURNAL OF EVALUATION IN CLINICAL PRACTICE, 2018, 24 (02) : 408 - 415
  • [3] Variable Importance Matching for Causal Inference
    Lanners, Quinn
    Parikh, Harsh
    Volfovsky, Alexander
    Rudin, Cynthia
    Page, David
    [J]. UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2023, 216 : 1174 - 1184
  • [4] Causal Inference in Auditing: A Framework
    Srivastava, Rajendra P.
    Mock, Theodore J.
    Pincus, Karen V.
    Wright, Arnold M.
    [J]. AUDITING-A JOURNAL OF PRACTICE & THEORY, 2012, 31 (03): : 177 - 201
  • [5] The role of causal inference in health services research II: a framework for causal inference
    Moser, Andre
    Puhan, Milo A.
    Zwahlen, Marcel
    [J]. INTERNATIONAL JOURNAL OF PUBLIC HEALTH, 2020, 65 (03) : 367 - 370
  • [6] Handbook of matching and weighting adjustments for causal inference
    Lee, Youjin
    [J]. BIOMETRICS, 2024, 80 (03)
  • [7] Handbook of Matching and Weighting Adjustments for Causal Inference
    Wong, Raymond K. W.
    Zubizarreta, Jose R.
    Stuart, Elizabeth A.
    Small, Dylan S.
    Rosenbaum, Paul R.
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2024, 119 (545) : 791 - 791
  • [8] Observation weights matching approach for causal inference
    Lee, Kangbok
    Han, Sumin
    Baik, Hyeoncheol
    Jeong, Yeasung
    Park, Young Woong
    [J]. PATTERN RECOGNITION, 2024, 154
  • [9] Opiates for the Matches: Matching Methods for Causal Inference
    Sekhon, Jasjeet S.
    [J]. ANNUAL REVIEW OF POLITICAL SCIENCE, 2009, 12 : 487 - 508
  • [10] Matching algorithms for causal inference with multiple treatments
    Scotina, Anthony D.
    Gutman, Roee
    [J]. STATISTICS IN MEDICINE, 2019, 38 (17) : 3139 - 3167