Estimation of the additive hazards model with interval-censored data and missing covariates
Estimation of the additive hazards model with interval-censored data and missing covariates
复制标题
使用区间删失数据和缺失协变量估计加性风险模型
DOI：
10.1002/cjs.11544
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Jianguo Sun
中科院分区：
文献类型：
--
作者：
Huiqiong Li;Han Zhang;Liang Zhu;Ni Li;Jianguo Sun
加性危害模型是失效时间数据分析中最常用的回归模型之一，人们已经开发了多种方法对其进行推理。然而，当存在协变量缺失值且观测到的响应是区间截尾时，不存在既定的估计程序；这两种类型的并发症出现在各种情况下，包括人口、流行病学、金融、医学和社会学研究。为了解决这一缺陷，我们提出了几种基于逆概率加权和基于重加权的估计方法，用于随机丢失协变量值的情况。结果表明，回归模型参数的估计量是一致的和渐近正态的。模拟研究的数值结果表明，所提出的方法在实际情况下是有效的。提供了儿童癌症生存研究的应用程序。加拿大统计杂志48:499-517；2020©2020加拿大统计学会
The additive hazards model is one of the most commonly used regression models in the analysis of failure time data and many methods have been developed for its inference in various situations. However, no established estimation procedure exists when there are covariates with missing values and the observed responses are interval‐censored; both types of complications arise in various settings including demographic, epidemiological, financial, medical and sociological studies. To address this deficiency, we propose several inverse probability weight‐based and reweighting‐based estimation procedures for the situation where covariate values are missing at random. The resulting estimators of regression model parameters are shown to be consistent and asymptotically normal. The numerical results that we report from a simulation study suggest that the proposed methods work well in practical situations. An application to a childhood cancer survival study is provided.The Canadian Journal of Statistics48: 499–517; 2020 © 2020 Statistical Society of Canada