Recurrent event data frequently arise in longitudinal studies and observations on recurrent events could be terminated by a major failure event such as death. In many situations, there exist a large fraction of subjects without any recurrent events of interest. Among these subjects, some are unsusceptible to recurrent events, while others are susceptible but have no recurrent events being observed due to censoring. In this article, we propose a zero-inflated generalized joint frailty model and a sieve maximum likelihood approach to analyze zero-inflated recurrent events with a terminal event. The model provides a considerable flexibility in formulating the effects of covariates on both recurrent events and the terminal event by specifying various transformation functions. In addition, Bernstein polynomials are employed to approximate the unknown cumulative baseline hazard (intensity) function. The estimation procedure can be easily implemented and is computationally fast. Extensive simulation studies are conducted and demonstrate that our proposed method works well for practical situations. Finally, we apply the method to analyze myocardial infarction recurrences in the presence of death in a clinical trial with cardiovascular outcomes.

中文翻译：

---

具有终末事件的零膨胀复发事件的半参数分析

纵向研究中经常出现复发事件数据，对复发事件的观察可能会因重大失败事件（例如死亡）而终止。在许多情况下，存在很大一部分受试者没有任何感兴趣的复发事件。在这些受试者中，有些受试者对复发性事件不敏感，而另一些受试者易感但由于审查而没有观察到复发性事件。在本文中，我们提出了一种零膨胀广义关节衰弱模型和筛子最大似然方法来分析具有终末事件的零膨胀复发事件。该模型通过指定各种转换函数，在制定协变量对复发事件和终止事件的影响方面提供了相当大的灵活性。此外，伯恩斯坦多项式用于逼近未知的累积基线风险（强度）函数。估计过程可以很容易地实现并且计算速度很快。进行了广泛的模拟研究，并证明我们提出的方法适用于实际情况。最后，我们应用该方法在具有心血管结果的临床试验中分析存在死亡的心肌梗塞复发。