Longitudinal Mixed Membership trajectory models for disability survey data

TL;DR

This paper introduces longitudinal mixed membership models to analyze disability progression over time, revealing late disability onset and intergenerational differences in the elderly population.

Contribution

It develops novel mixed membership trajectory models incorporating cohort effects for analyzing multivariate longitudinal disability data.

Findings

Most individuals experience late disability onset.

Younger cohorts develop disabilities later in life.

Inter-generational differences in disability trajectories.

Abstract

We develop methods for analyzing discrete multivariate longitudinal data and apply them to functional disability data on the U.S. elderly population from the National Long Term Care Survey (NLTCS), 1982-2004. Our models build on a Mixed Membership framework, in which individuals are allowed multiple membership on a set of extreme profiles characterized by time-dependent trajectories of progression into disability. We also develop an extension that allows us to incorporate birth-cohort effects, in order to assess inter-generational changes. Applying these methods, we find that most individuals follow trajectories that imply a late onset of disability, and that younger cohorts tend to develop disabilities at a later stage in life compared to their elders.