Subgroup Identification and Regression Analysis of Clustered and Heterogeneous Interval-Censored Data

Clustered and heterogeneous interval-censored data occur in many fields such as medical studies. For example, a migraine study with the Netherlands Twin Registry, information including time to diagnosis of gender was collected for 3975 monozygotic dizygotic twins. Since each subject is observed only at discrete periodic follow-up points, failure times interest (i.e., when individual first had migraine) are known belong certain intervals hence interval-censored. Furthermore, these twins come from different genetic backgrounds may be associated differential risks developing migraines. simultaneous subgroup identification regression analysis data, we propose latent Cox model where number subgroups not assumed priori but rather data-driven estimated. The nonparametric maximum likelihood method an EM algorithm monotone ascent property also developed estimating parameters. Simulation studies conducted assess finite sample performance proposed estimation procedure. We further illustrate methodologies by empirical data.