Fan Xinyan, Liu Mengque, Fang Kuangnan, Huang Yuan, Ma Shuangge
1 School of Economics, Xiamen University, Xiamen, China.
2 Department of Biostatistics, Yale University, New Haven, CT, USA.
Stat Methods Med Res. 2017 Oct;26(5):2078-2092. doi: 10.1177/0962280217708684. Epub 2017 May 8.
Cure rate models have been widely adopted for characterizing survival data that have long-term survivors. Under a mixture cure rate model where the population is a mixture of cured and susceptible subjects, a primary goal is to study covariate effects on the cure probability and survival function of the susceptible subjects. In this article, we propose a penalization method for estimating the mixture cure rate model where we explicitly consider the structural effects of covariates. The proposed method is more informative than the standard estimations and more flexible than the existing works on structural effects. Depending on data characteristics, we develop different penalties and corresponding computational algorithms. Simulation shows that the proposed method outperforms the alternatives by more accurately estimating parameters and identifying relevant variables. Two breast cancer datasets, one with low-dimensional clinical variables and the other with high-dimensional genetic variables, are analyzed.
治愈率模型已被广泛用于刻画具有长期存活者的生存数据。在混合治愈率模型下，总体由治愈者和易感者混合组成，一个主要目标是研究协变量对易感者治愈概率和生存函数的影响。在本文中，我们提出一种惩罚方法来估计混合治愈率模型，其中我们明确考虑了协变量的结构效应。所提出的方法比标准估计更具信息性，并且比现有关于结构效应的工作更灵活。根据数据特征，我们开发了不同的惩罚项和相应的计算算法。模拟表明，所提出的方法通过更准确地估计参数和识别相关变量，优于其他方法。我们分析了两个乳腺癌数据集，一个具有低维临床变量，另一个具有高维基因变量。
