Dayu Sun, Yuanyuan Guo, Yang Li, Jianguo Sun, Wanzhu Tu
{"title":"A flexible time-varying coefficient rate model for panel count data.","authors":"Dayu Sun, Yuanyuan Guo, Yang Li, Jianguo Sun, Wanzhu Tu","doi":"10.1007/s10985-024-09630-1","DOIUrl":null,"url":null,"abstract":"<p><p>Panel count regression is often required in recurrent event studies, where the interest is to model the event rate. Existing rate models are unable to handle time-varying covariate effects due to theoretical and computational difficulties. Mean models provide a viable alternative but are subject to the constraints of the monotonicity assumption, which tends to be violated when covariates fluctuate over time. In this paper, we present a new semiparametric rate model for panel count data along with related theoretical results. For model fitting, we present an efficient EM algorithm with three different methods for variance estimation. The algorithm allows us to sidestep the challenges of numerical integration and difficulties with the iterative convex minorant algorithm. We showed that the estimators are consistent and asymptotically normally distributed. Simulation studies confirmed an excellent finite sample performance. To illustrate, we analyzed data from a real clinical study of behavioral risk factors for sexually transmitted infections.</p>","PeriodicalId":49908,"journal":{"name":"Lifetime Data Analysis","volume":null,"pages":null},"PeriodicalIF":1.2000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Lifetime Data Analysis","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.1007/s10985-024-09630-1","RegionNum":3,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/28 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"MATHEMATICS, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
Panel count regression is often required in recurrent event studies, where the interest is to model the event rate. Existing rate models are unable to handle time-varying covariate effects due to theoretical and computational difficulties. Mean models provide a viable alternative but are subject to the constraints of the monotonicity assumption, which tends to be violated when covariates fluctuate over time. In this paper, we present a new semiparametric rate model for panel count data along with related theoretical results. For model fitting, we present an efficient EM algorithm with three different methods for variance estimation. The algorithm allows us to sidestep the challenges of numerical integration and difficulties with the iterative convex minorant algorithm. We showed that the estimators are consistent and asymptotically normally distributed. Simulation studies confirmed an excellent finite sample performance. To illustrate, we analyzed data from a real clinical study of behavioral risk factors for sexually transmitted infections.
在经常性事件研究中经常需要进行面板计数回归,其目的是建立事件发生率模型。由于理论和计算上的困难,现有的比率模型无法处理时变协变量效应。均值模型提供了一个可行的替代方案,但受到单调性假设的限制,当协变量随时间波动时,单调性假设往往会被违反。在本文中,我们针对面板计数数据提出了一种新的半参数率模型以及相关的理论结果。在模型拟合方面,我们提出了一种高效的 EM 算法,其中包含三种不同的方差估计方法。该算法使我们能够避开数值积分的挑战和迭代凸小法算法的困难。我们的研究表明,这些估计值是一致的,并具有渐近正态分布。模拟研究证实了其出色的有限样本性能。为了说明这一点,我们分析了一项关于性传播感染行为风险因素的真实临床研究数据。
期刊介绍:
The objective of Lifetime Data Analysis is to advance and promote statistical science in the various applied fields that deal with lifetime data, including: Actuarial Science – Economics – Engineering Sciences – Environmental Sciences – Management Science – Medicine – Operations Research – Public Health – Social and Behavioral Sciences.