Abstract

Interval-censored survival data arise naturally in many fields such as medical follow-up studies, in which the event or failure is not observed exactly but only known to occur within a time interval. Most existing approaches for analyzing interval-censored failure time data assume that the examination times and the failure time are independent or conditionally independent given covariates. While this assumption offers considerable simplification, it is not plausible in some situations, e.g., the visiting rate can be positively or negatively correlated with the risk of failure due to unobservable health status even after adjusting for observable covariates. In this article, we consider dependent interval-censored data, where there exists dependence between the failure time and the entire visiting process. A shared frailty is used to characterize the dependence of hazard function of failure time and intensity function of visiting process. Moreover, the joint model could describe the possible none, positive or negative association between failure time and visiting process. We propose the semiparametric maximum likelihood estimators and develop an EM algorithm based on a Poisson data augmentation. The performance of the proposed method is examined through extensive simulation studies and an application to a bladder cancer dataset is presented.

摘要

间隔删失的生存数据自然出现在许多领域，例如医学随访研究，在这些领域中，事件或故障没有被准确地观察到，而是只知道在一个时间间隔内发生。大多数现有的分析间隔删失故障时间数据的方法都假设检查时间和故障时间是独立的或条件独立的给定协变量。虽然这个假设提供了相当大的简化，但在某些情况下它是不合理的，例如，即使在调整了可观察的协变量之后，访问率也可能与由于不可观察的健康状况而导致的失败风险正或负相关。在本文中，我们考虑依赖区间删失数据，其中故障时间与整个访问过程之间存在依赖关系。一个共享脆弱性用于表征故障时间的危险函数和访问过程的强度函数的依赖性。此外，联合模型可以描述故障时间和访问过程之间可能存在的无关联、正关联或负关联。我们提出了半参数最大似然估计器，并开发了一种基于泊松数据增强的 EM 算法。通过广泛的模拟研究检查了所提出方法的性能，并提出了对膀胱癌数据集的应用。我们提出了半参数最大似然估计器，并开发了一种基于泊松数据增强的 EM 算法。通过广泛的模拟研究检查了所提出方法的性能，并提出了对膀胱癌数据集的应用。我们提出了半参数最大似然估计器，并开发了一种基于泊松数据增强的 EM 算法。通过广泛的模拟研究检查了所提出方法的性能，并提出了对膀胱癌数据集的应用。