Conditional Copula Models for Right-Censored Clustered Event Time Data

TL;DR

This paper introduces a new modeling approach using conditional copulas to analyze how covariates influence the dependence structure of right-censored clustered event times, with estimation and testing strategies validated through simulations and applied to medical data.

Contribution

It develops a flexible local likelihood estimation method for covariate-dependent copula parameters and a formal testing procedure for their constancy in right-censored clustered data.

Findings

Effective estimation of covariate effects on dependence structure demonstrated in simulations.

The testing procedure accurately detects changes in copula parameters across covariate values.

Application to medical data reveals significant covariate influence on event dependence.

Abstract

This paper proposes a modelling strategy to infer the impact of a covariate on the dependence structure of right-censored clustered event time data. The joint survival function of the event times is modelled using a parametric conditional copula whose parameter depends on a cluster-level covariate in a functional way. We use a local likelihood approach to estimate the form of the copula parameter and outline a generalized likelihood ratio-type test strategy to formally test its constancy. A bootstrap procedure is employed to obtain an approximate $p$-value for the test. The performance of the proposed estimation and testing methods are evaluated in simulations under different rates of right-censoring and for various parametric copula families, considering both parametrically and nonparametrically estimated margins. We apply the methods to data from the Diabetic Retinopathy Study to assess the impact of disease onset age on the loss of visual acuity.