Efficiently transporting causal (in)direct effects to new populations\n under intermediate confounding and with multiple mediators

2020/06/13 by Kara E. Rudolph, Iván Díaz, Rudolph, Kara E. +1
Mathematics · #Advanced Causal Inference Techniques #FOS: Computer and information sciences #Methodology (stat.ME) #Statistical Methods and Bayesian Inference #Statistical Methods and Inference

paper · pdf · doi:10.48550/arxiv.2006.07708

openalex publication_date 2020/06/13 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28

Abstract

The same intervention can produce different effects in different sites.\nTransport mediation estimators can estimate the extent to which such\ndifferences can be explained by differences in compositional factors and the\nmechanisms by which mediating or intermediate variables are produced; however,\nthey are limited to consider a single, binary mediator. We propose novel\nnonparametric estimators of transported stochastic (in)direct effects that\nconsider multiple, high-dimensional mediators and intermediate variables. They\nare multiply robust, efficient, asymptotically normal, and can incorporate\ndata-adaptive estimation of nuisance parameters. They can be applied to\nunderstand differences in treatment effects across sites and/or to predict\ntreatment effects in a target site based on outcome data in source sites.\n

Related

• Nonparametric estimators of interventional (transported) direct and indirect effects that accommodate multiple mediators and multiple intermediate confounders
• Nonparametric Estimation of Mediation Effects with A General Treatment
• Semiparametric Estimation for Causal Mediation Analysis with Multiple Causally Ordered Mediators
• Multiply Robust Causal Mediation Analysis with Continuous Treatments
• On Efficient Inference of Causal Effects with Multiple Mediators