Longitudinal quantile regression in presence of informative drop-out through longitudinal-survival joint modeling

TL;DR

This paper introduces a flexible joint modeling approach for longitudinal quantile regression with informative drop-out, combining survival and repeated measures data using Monte Carlo EM, applicable under various distributional assumptions.

Contribution

It presents a novel joint model linking quantile regression and survival analysis to handle informative drop-out in longitudinal data.

Findings

Effective handling of informative drop-out in simulations.

Application to cardiomyopathy data demonstrates model utility.

Flexible modeling under diverse distributional assumptions.

Abstract

We propose a joint model for a time-to-event outcome and a quantile of a continuous response repeatedly measured over time. The quantile and survival processes are associated via shared latent and manifest variables. Our joint model provides a flexible approach to handle informative drop-out in quantile regression. A general Monte Carlo Expectation Maximization strategy based on importance sampling is proposed, which is directly applicable under any distributional assumption for the longitudinal outcome and random effects, and parametric and non-parametric assumptions for the baseline hazard. Model properties are illustrated through a simulation study and an application to an original data set about dilated cardiomyopathies.