带相依终止事件的复发事件数据的可加可乘比率模型

An Additive-Multiplicative Rates Model for Recurrent Event Data with a Terminal Event

本文对带相依终止事件的复发事件数据提出了一个联合建模分析方法,用一个带脆弱变量的可加可乘比率模型来刻画复发事件过程,还用带脆弱变量的Cox风险率模型来刻画终止事件过程,而且这两个过程的相依性由脆弱变量来刻画.我们利用估计方程的方法,对模型参数进行了估计,给出了所得估计的渐近性质.同时,通过数值模拟分析验证了估计的渐近性质.最后,利用该方法分析了弗吉尼亚大学慢性心脏病病人医疗诊费数据.

We propose a joint modeling approach for the analysis of recurrent event data with a terminal event, where an additive-multiplicative rates model is specified for the recurrent event process, the Cox hazards frailty model is specified for the terminal event, and the shared frailty is used to account for the association between the two processes. An estimating equation approach is developed for estimating the model parameters. The asymptotic properties of the proposed estimators are established.Simulation studies are constructed to examine performances of the proposed estimators under finite samples. Finally, we use the proposed method to analyze a medical cost study of chronic heart failure patients.