Copula Modeling of Multivariate Longitudinal Data with Dropout

TL;DR

This paper introduces a copula-based generalized method of moments approach for modeling multivariate longitudinal data with dropout, providing new insights for risk management in biomedical and insurance applications.

Contribution

It presents a novel copula-based estimation method for joint longitudinal and dropout data, validated through simulations and illustrated with insurance data.

Findings

The method accurately estimates dependence parameters.

Simulation results confirm the approach's viability.

Application demonstrates improved risk management insights.

Abstract

Joint multivariate longitudinal and time-to-event data are gaining increasing attention in the biomedical sciences where subjects are followed over time to monitor the progress of a disease or medical condition. In the insurance context, claims outcomes may be related to a policyholder's dropout or decision to lapse a policy. This paper introduces a generalized method of moments technique to estimate dependence parameters where associations are represented using copulas. A simulation study demonstrates the viability of the approach. The paper describes how the joint model provides new information that insurers can use to better manage their portfolios of risks using illustrative data from a Spanish insurer.