Discrete-Time Survival Factor Mixture Analysis for Low-Frequency Recurrent Event Histories

Abstract

In this article, the latent class analysis framework for modeling single event discrete-time survival data is extended to low-frequency recurrent event histories. A partial gap time model, parameterized as a restricted factor mixture model, is presented and illustrated using juvenile offending data. This model accommodates event-specific baseline hazard probabilities and covariate effects; event recurrences within a single time period; and accounts for within- and between-subject correlations of event times. This approach expands the family of latent variable survival models in a way that allows researchers to explicitly address questions about unobserved heterogeneity in the timing of events across the lifespan.

ACKNOWLEDGMENT

This research was supported in part by grant T32-MH018834 from National Institute of Mental Health. The work has benefitted from discussions in the Prevention Science and Methodology Group (Designs and Analyses for Mental Health Preventive Trials, NIDA and NIMH R01-MH40859). Special thanks to Bengt Muthén and Klaus Larsen for helpful comments on earlier versions; to Hanno Petras and Weiwei Liu for their interest and effort in finding applications for this methodology in their own criminology research; and especially to Nilam Ram for his exceptional patience with the process of preparing this manuscript for inclusion in this special issue.

Notes