Counting Process Based Dimension Reduction Methods for Censored Outcomes

TL;DR

This paper introduces a novel counting process-based dimension reduction method for censored survival data that avoids estimating the censoring distribution and addresses the curse of dimensionality, with proven asymptotic properties and practical efficiency.

Contribution

It develops a new semiparametric approach for dimension reduction in censored data that improves over existing methods by eliminating bias and reducing computational complexity.

Findings

Significantly improved estimation accuracy in simulations.

Efficient estimation requiring only singular value decomposition.

Successful application to melanoma dataset.

Abstract

We propose a class of dimension reduction methods for right censored survival data using a counting process representation of the failure process. Semiparametric estimating equations are constructed to estimate the dimension reduction subspace for the failure time model. The proposed method addresses two fundamental limitations of existing approaches. First, using the counting process formulation, it does not require any estimation of the censoring distribution to compensate the bias in estimating the dimension reduction subspace. Second, the nonparametric part in the estimating equations is adaptive to the structural dimension, hence the approach circumvents the curse of dimensionality. Asymptotic normality is established for the obtained estimators. We further propose a computationally efficient approach that simplifies the estimation equation formulations and requires only a singular value decomposition to estimate the dimension reduction subspace. Numerical studies suggest that our new approaches exhibit significantly improved performance for estimating the true dimension reduction subspace. We further conduct a real data analysis on a skin cutaneous melanoma dataset from The Cancer Genome Atlas. The proposed method is implemented in the R package "orthoDr".