A0591
Title: A debiased estimator for the mediation functional in (ultra) high-dimension in the presence of interaction effects
Authors: Debarghya Mukherjee - Boston University (United States) [presenting]
AmirEmad Ghassami - Boston University (United States)
Shi Bo - Boston University (United States)
Abstract: Mediation analysis is a crucial tool for uncovering the mechanisms through which a treatment affects the outcome, providing deeper causal insights and guiding effective interventions. Despite advances in analyzing the mediation effect with fixed/low-dimensional mediators and covariates, the understanding of estimation and inference of mediation functional in the presence of (ultra)-high-dimensional mediators and covariates is still limited. An estimator is presented for mediation functional in a high-dimensional setting that accommodates the interaction between covariates and treatment in generating mediators, as well as interactions between both covariates and treatment and mediators and treatment in generating the response. It is demonstrated that the estimator is $\sqrt{n}$-consistent and asymptotically normal, thus enabling reliable inference on direct and indirect treatment effects with asymptotically valid confidence intervals. A key technical contribution is the development of a multi-step debiasing technique, which may also be valuable in other statistical settings with similar structural complexities where accurate estimation depends on debiasing. The proposed methodology is evaluated through extensive simulation studies and is applied to the TCGA lung cancer dataset to estimate the effect of smoking, mediated by DNA methylation, on the survival time of lung cancer patients.
