Approximate Bayesian Inference for Doubly Robust Estimation

被引:19
|
作者
Graham, Daniel J. [1 ]
McCoy, Emma J. [2 ]
Stephens, David A. [3 ]
机构
[1] Univ London Imperial Coll Sci Technol & Med, Dept Civil Engn, London SW7 2AZ, England
[2] Univ London Imperial Coll Sci Technol & Med, Dept Math, London SW7 2AZ, England
[3] McGill Univ, Dept Math & Stat, Montreal, PQ, Canada
来源
BAYESIAN ANALYSIS | 2016年 / 11卷 / 01期
关键词
approximate bayes; doubly robust; propensity score; treatment effect; PROPENSITY SCORE; MODELS;
D O I
10.1214/14-BA928
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Doubly robust estimators are typically constructed by combining outcome regression and propensity score models to satisfy moment restrictions that ensure consistent estimation of causal quantities provided at least one of the component models is correctly specified. Standard Bayesian methods are difficult to apply because restricted moment models do not imply fully specified likelihood functions. This paper proposes a Bayesian bootstrap approach to derive approximate posterior predictive distributions that are doubly robust for estimation of causal quantities. Simulations show that the approach performs well under various sources of misspecification of the outcome regression or propensity score models. The estimator is applied in a case study of the effect of area deprivation on the incidence of child pedestrian casualties in British cities.
引用
收藏
页码:47 / 69
页数:23
相关论文
共 50 条
  • [41] Adversarial α-divergence minimization for Bayesian approximate inference
    Rodriguez-Santana, Simon
    Hernandez-Lobato, Daniel
    NEUROCOMPUTING, 2022, 471 : 260 - 274
  • [42] ON BARTLETT ADJUSTMENTS FOR APPROXIMATE BAYESIAN-INFERENCE
    DICICCIO, TJ
    STERN, SE
    BIOMETRIKA, 1993, 80 (04) : 731 - 740
  • [43] Approximate inference on optimized quantum Bayesian networks
    Fathallah, Walid
    Amor, Nahla Ben
    Leray, Philippe
    International Journal of Approximate Reasoning, 2024, 175
  • [44] Approximate Bayesian Inference Based on Expected Evaluation
    Hammer, Hugo L.
    Riegler, Michael A.
    Tjelmeland, Hakon
    BAYESIAN ANALYSIS, 2024, 19 (03): : 677 - 698
  • [45] Stochastic Gradient Descent as Approximate Bayesian Inference
    Mandt, Stephan
    Hoffman, Matthew D.
    Blei, David M.
    JOURNAL OF MACHINE LEARNING RESEARCH, 2017, 18
  • [47] Approximate Slice Sampling for Bayesian Posterior Inference
    DuBois, Christopher
    Korattikara, Anoop
    Welling, Max
    Smyth, Padhraic
    ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 33, 2014, 33 : 185 - 193
  • [48] Evaluating Approximate Inference in Bayesian Deep Learning
    Wilson, Andrew Gordon
    Lotfi, Sanae
    Vikram, Sharad
    Hoffman, Matthew D.
    Gal, Yarin
    Li, Yingzhen
    Pradier, Melanie F.
    Foong, Andrew
    Farquhar, Sebastian
    Izmailov, Pavel
    NEURIPS 2021 COMPETITIONS AND DEMONSTRATIONS TRACK, VOL 176, 2021, 176 : 113 - 124
  • [49] Approximate Bayesian Inference in Semiparametric Copula Models
    Grazian, Clara
    Liseo, Brunero
    BAYESIAN ANALYSIS, 2017, 12 (04): : 991 - 1016
  • [50] Enhanced Doubly Robust Procedure for Causal Inference
    Yuan, Ao
    Yin, Anqi
    Tan, Ming T.
    STATISTICS IN BIOSCIENCES, 2021, 13 (03) : 454 - 478