Survival analysis using auxiliary variables via non-parametric multiple imputation
Survival analysis using auxiliary variables via non-parametric multiple imputation
复制标题
DOI：
10.1002/sim.2452
复制
发表时间：
2006-10-30
影响因子：
2
通讯作者：
Commenges, Daniel
中科院分区：
文献类型：
--
作者：
Hsu, Chiu-Hsieh;Taylor, Jeremy M. G.;Commenges, Daniel
我们发展了一种基于多重补偿的方法，在生存分析中使用辅助变量来估计边际生存分布，以恢复删失观测的信息。为了进行推算，我们使用两个有效的生存模型来定义最近邻推算风险集。一种模型用于事件时间，另一种模型用于审查时间。基于归并风险集，考虑了两种非参数多重归算方法：风险集归并方法和Kaplan-Meier归并方法。对于这两种方法，每个被审查的观测都被归因于未来的事件或审查时间。在有一个分类辅助变量的情况下，我们证明了在大量推算的情况下，由Kaplan-Meier推算方法得到的估计对应于加权Kaplan-Meier估计。我们还证明了Kaplan-Meier推算方法对两个工作模型中的任何一个的错误指定都是稳健的。在具有独立于时间和依赖于时间的辅助变量的模拟研究中，我们比较了多重补偿方法和截尾加权方法的逆概率。结果表明，所有方法都能减少因依赖截尾而产生的偏差，提高了效率。我们将这些方法应用于艾滋病临床试验数据，比较ZDV和安慰剂，其中CD4计数是时间依赖的辅助变量。版权所有(C)2005 John Wiley&Sons。LTD.
We develop an approach, based on multiple imputation, that estimates the marginal survival distribution in survival analysis using auxiliary variables to recover information for censored observations. To conduct the imputation, we use two working survival models to define a nearest neighbour imputing risk set. One model is for the event times and the other for the censoring times. Based on the imputing risk set, two non-parametric multiple imputation methods are considered: risk set imputation, and Kaplan-Meier imputation. For both methods a future event or censoring time is imputed for each censored observation. With a categorical auxiliary variable, we show that with a large number of imputes the estimates from the Kaplan-Meier imputation method correspond to the weighted Kaplan-Meier estimator. We also show that the Kaplan-Meier imputation method is robust to mis-specification of either one of the two working models. In a simulation study with time independent and time-dependent auxiliary variables, we compare the multiple imputation approaches with an inverse probability of censoring weighted method. We show that all approaches can reduce bias due to dependent censoring and improve the efficiency. We apply the approaches to AIDS clinical trial data comparing ZDV and placebo, in which CD4 count is the time-dependent auxiliary variable. Copyright (c) 2005 John Wiley & Sons. Ltd.