Handling non-ignorable dropouts in longitudinal data: A conditional model based on a latent Markov heterogeneity structure

TL;DR

This paper introduces a novel conditional model for analyzing longitudinal data with non-ignorable dropouts, using a latent Markov structure to account for unobserved heterogeneity and dependence between missing data and observed outcomes.

Contribution

It proposes a new conditional dropout model with a latent Markov process, estimated via EM algorithm, to handle non-ignorable missing data in longitudinal studies.

Findings

Model effectively captures unobserved heterogeneity.

Performs well in simulations and real data application.

Outperforms some existing methods in handling non-ignorable dropouts.

Abstract

We illustrate a class of conditional models for the analysis of longitudinal data suffering attrition in random effects models framework, where the subject-specific random effects are assumed to be discrete and to follow a time-dependent latent process. The latent process accounts for unobserved heterogeneity and correlation between individuals in a dynamic fashion, and for dependence between the observed process and the missing data mechanism. Of particular interest is the case where the missing mechanism is non-ignorable. To deal with the topic we introduce a conditional to dropout model. A shape change in the random effects distribution is considered by directly modeling the effect of the missing data process on the evolution of the latent structure. To estimate the resulting model, we rely on the conditional maximum likelihood approach and for this aim we outline an EM algorithm. The proposal is illustrated via simulations and then applied on a dataset concerning skin cancers. Comparisons with other well-established methods are provided as well.