Non-marginal feature screening for additive hazard model with ultrahigh-dimensional covariates

Abstract

Survival data with ultrahigh-dimensional covariates have been frequently encountered in medical studies and other fields. In this article, we propose a non-marginal feature screening procedure for the additive hazard model with ultrahigh-dimensional covariates. The proposed method utilizes the joint effects between covariates, which can effectively identify active covariates that are jointly dependent but marginally independent of the response. We develop an iterative hard-thresholding (IHT) algorithm to effectively implement the proposed procedure. Its convergence properties were investigated rigorously and further proved that the proposed procedure possesses the sure screening property. We conduct Monte Carlo simulation to evaluate the finite sample performance of the proposed procedure, and demonstrate the proposed procedure through an empirical analysis of a real data example.