Joint analysis of informatively interval-censored failure time and panel count data.

Release time:2022-12-14  Hits:

• Affiliation of Author(s):数学与统计学院
• Teaching and Research Group:统计教研室
• Journal:Statistical Methods in Medical Research
• Funded by:国家自然科学基金项目
• Key Words:Bernstein polynomial;Event history study;Frailty model;Sieve maximum likelihood estimation
• Abstract:Interval-censored failure time and panel count data, which frequently arise in medical studies and social sciences, are two types of important incomplete data. Although methods for their joint analysis have been available in the literature, they did not consider the observation process, which may depend on the failure time and/or panel count of interest. This study considers a three-component joint model to analyze interval-censored failure time, panel counts, and the observation process within a unique framework. Gamma and distribution-free frailties are introduced to jointly model the interdependency among the interval-censored data, panel count data, and the observation process. We propose a sieve maximum likelihood approach coupled with Bernstein polynomial approximation to estimate the unknown parameters and baseline hazard function. The asymptotic properties of the resulting estimators are established. An extensive simulation study suggests that the proposed procedure works well for practical situations. An application of the method to a real-life dataset collected from a cardiac allograft vasculopathy study is presented.
• Indexed by:Journal paper
• Volume:31
• Issue:11
• Page Number:2054-2068
• Translation or Not:no
• Date of Publication:2022-07-12
• Included Journals:SCI