Joint model for bivariate zero-inflated recurrent event data with terminal events. Issue 4 (12th March 2021)

• Record Type: Journal Article
• Authors: Kim, Yang-Jin
• Is Part Of: Journal of applied statistics. Volume 48:Issue 4(2021)
• Page Start: 738
• Page End: 749
• Publication Date: 2021-03-12
• Subjects: Bivariate recurrent event -- cure rate model -- frailty effect -- joint model -- piecewise baseline -- terminal event; Statistics -- Periodicals; 519.5
• DOI: 10.1080/02664763.2020.1744539
• Languages: English
• ISSNs: 0266-4763

Abstract

Abstract : Bivariate recurrent event data are observed when subjects are at risk of experiencing two different type of recurrent events. In this paper, our interest is to suggest statistical model when there is a substantial portion of subjects not experiencing recurrent events but having a terminal event. In a context of recurrent event data, zero events can be related with either the risk free group or a terminal event. For simultaneously reflecting both a zero inflation and a terminal event in a context of bivariate recurrent event data, a joint model is implemented with bivariate frailty effects. Simulation studies are performed to evaluate the suggested models. Infection data from AML (acute myeloid leukemia) patients are analyzed as an application.