A1128
Title: Sparse causal mediation analysis with unmeasured mediator-outcome confounding
Authors: Wei Li - Renmin University of China (China) [presenting]
Abstract: Causal mediation analysis aims to investigate how an intermediary factor called a mediator regulates the causal effect of a treatment on an outcome. With the increasing availability of measurements on a large number of potential mediators in various disciplines, methods for conducting mediation analysis with many or even high-dimensional mediators have been proposed. However, they often assume there is no unmeasured confounding between mediators and the outcome. Such confounding is allowed, and an approach is provided to address both identification and mediator selection problems under the structural equation modelling framework. The identification strategy involves constructing a pseudo proxy variable for unmeasured confounding based on a latent factor model for multiple mediators. Using this proxy variable, a partially penalized procedure is proposed to select important mediators with nonzero effects on the outcome. The resultant estimates are consistent, and the estimates of nonzero parameters are asymptotically normal. Simulation studies show the advantageous performance of the proposed procedure over other existing methods. Finally, this approach is applied to genomic data, and gene expressions that may actively mediate the effect of a genetic variant on mouse obesity are identified.
