Testing mediation effects using logic of Boolean matrices

Tue March 1st 2022, 4:30pm
Sloan 380C
Lexin Li, UC Berkeley

A central question in high-dimensional mediation analysis is to infer the significance of individual mediators. The main challenge is that the total number of potential paths that go through any mediator is super-exponential in the number of mediators. Most existing mediation inference solutions either explicitly impose that the mediators are conditionally independent given the exposure, or ignore any potential directed paths among the mediators. In this talk, we present a novel hypothesis testing procedure to evaluate individual mediation effects, while taking into account potential interactions among the mediators. Our key idea is to construct the test statistic using the logic of Boolean matrices, which enables us to establish the proper limiting distribution under the null hypothesis. We further employ screening, data splitting, and decorrelated estimation to reduce the bias and increase the power of the test. We show that our test can control both the size and false discovery rate asymptotically, and the power of the test approaches one, while allowing the number of mediators to diverge to infinity with the sample size. In this talk, I also give a brief overview of some of our recent neuroimaging-related projects on ordinary differential equations, point process modeling, functional graphical modeling, kernel knockoffs, and multi-modality analysis.

Zoom Recording [SUNet/SSO authentication required]