Cox regression analysis for distorted covariates with an unknown distortion function

TL;DR

This paper introduces a new Cox regression model that corrects for covariate distortion using kernel smoothing and maximum likelihood estimation, improving inference accuracy in censored survival data.

Contribution

It proposes a novel covariate-adjusted Cox model with unknown distortion functions and establishes its large sample properties, addressing bias correction in distorted covariate data.

Findings

Estimator performs well in simulations

Corrects bias from covariate distortion

Demonstrated on real NWTS data

Abstract

We study inference for censored survival data where some covariates are distorted by some unknown functions of an observable confounding variable in a multiplicative form. Example of this kind of data in medical studies is the common practice to normalizing some important observed exposure variables by patients' body mass index (BMI), weight or age. Such phenomenon also appears frequently in environmental studies where ambient measure is used for normalization, and in genomic studies where library size needs to be normalized for next generation sequencing data. We propose a new covariate-adjusted Cox proportional hazards regression model and utilize the kernel smoothing method to estimate the distorting function, then employ an estimated maximum likelihood method to derive estimator for the regression parameters. We establish the large sample properties of the proposed estimator. Extensive simulation studies demonstrate that the proposed estimator performs well in correcting the bias arising from distortion. A real data set from the National Wilms' Tumor Study (NWTS) is used to illustrate the proposed approach.