A0981
Title: Maximum likelihood estimation for semiparametric regression models with interval-censored multistate data
Authors: Yu Gu - The University of Hong Kong (Hong Kong) [presenting]
Donglin Zeng - University of North Carolina at Chapel Hill (United States)
Gerardo Heiss - University of North Carolina at Chapel Hill (United States)
Danyu Lin - University of North Carolina at Chapel Hill (United States)
Abstract: Interval-censored multistate data arise in many studies of chronic diseases, where the health status of a subject can be characterized by a finite number of disease states and the transition between any two states is only known to occur over a broad time interval. Time-dependent covariates are potentially related to multistate processes through semiparametric proportional intensity models with random effects. Nonparametric maximum likelihood estimation is studied under general interval censoring and develop a stable EM algorithm. It is shown that the resulting parameter estimators are consistent and that the finite-dimensional components are asymptotically normal with a covariance matrix that attains the semiparametric efficiency bound and can be consistently estimated through profile likelihood. In addition, it is demonstrated through extensive simulation studies that the proposed numerical and inferential procedures perform well in realistic settings. Finally, an application to a major epidemiologic cohort study is provided.
