Rehman H, Chandra N, Jammalamadaka S Rao
Department of Statistics, Ramanujan School of Mathematical Sciences, Pondicherry University, Puducherry 605 014, India.
Department of Statistics and Applied Probability, University of California, Santa Barbara, CA, USA.
Healthc Anal (N Y). 2021 Nov;1:100006. doi: 10.1016/j.health.2021.100006. Epub 2021 Sep 28.
Survival data is being analysed here under the middle censoring scheme, using specifically quantile function modelling under competing risks. The use of middle censoring scheme has been shown to be very appropriate under the COVID-19 pandemic scenario. Cause-specific quantile inference under middle censoring is employed. Such quantile inferences are obtained through cumulative incidence function based on cause-specific proportional hazards model. The baseline lifetime is assumed to follow a very general parametric model namely the Weibull distribution, and is independent of the censoring mechanism. We obtain estimates of the unknown parameters and cause specific quantile functions under classical as well as a Bayesian set-up. A Monte Carlo simulation study assesses the relative performance of the different estimators. Finally, a real life data analysis is given for illustration of the proposed methods.
在此，我们根据中间删失方案对生存数据进行分析，具体采用竞争风险下的分位数函数建模。研究表明，在新冠疫情背景下，中间删失方案非常适用。我们采用中间删失下的特定病因分位数推断方法。此类分位数推断是通过基于特定病因比例风险模型的累积发病率函数获得的。假设基线生存期服从一个非常通用的参数模型，即威布尔分布，且与删失机制无关。我们在经典以及贝叶斯框架下获得未知参数和特定病因分位数函数的估计值。一项蒙特卡洛模拟研究评估了不同估计量的相对性能。最后，给出一个实际数据分析以说明所提出的方法。
Zotero 插件