Semiparametric Methods for Exposure Misclassification in Propensity Score-Based Time-to-Event Data Analysis

TL;DR

This paper introduces a semiparametric method to correct bias caused by exposure misclassification in propensity score-based Cox models for time-to-event data, improving accuracy in epidemiological studies.

Contribution

It proposes a novel estimating equation approach for bias correction due to exposure measurement error in survival analysis with propensity scores.

Findings

Simulation studies show improved bias correction and estimator performance.

Application to NHS data demonstrates practical utility in epidemiology.

Method is implemented in an accessible R package.

Abstract

In epidemiology, identifying the effect of exposure variables in relation to a time-to-event outcome is a classical research area of practical importance. Incorporating propensity score in the Cox regression model, as a measure to control for confounding, has certain advantages when outcome is rare. However, in situations involving exposure measured with moderate to substantial error, identifying the exposure effect using propensity score in Cox models remains a challenging yet unresolved problem. In this paper, we propose an estimating equation method to correct for the exposure misclassification-caused bias in the estimation of exposure-outcome associations. We also discuss the asymptotic properties and derive the asymptotic variances of the proposed estimators. We conduct a simulation study to evaluate the performance of the proposed estimators in various settings. As an illustration, we apply our method to correct for the misclassification-caused bias in estimating the association of PM2.5 level with lung cancer mortality using a nationwide prospective cohort, the Nurses' Health Study (NHS). The proposed methodology can be applied using our user-friendly R function published online.