Imputing missing covariate values for the Cox model.

Imputing missing covariate values for the Cox model.
复制标题

DOI:
10.1002/sim.3618
复制
发表时间:
2009-07-10
影响因子:
2
通讯作者:
Royston, Patrick
Royston, Patrick
中科院分区:
医学3区
文献类型:
--
作者:
White, Ian R.;Royston, Patrick

文献摘要

参考文献

被引文献

相似文献

多元归算是一种常用的缺失数据归算方法,在回归分析中,当协变量存在缺失值时,多元归算通常比完全案例分析更有效。可以使用不完全协变量的回归模型对其他协变量,更重要的是,对结果进行归算。对于生存结果,通常的做法是在imputation模型中使用事件指标D和观测事件的对数或审查时间T,但其基本原理尚不清楚。我们假设生存结果遵循给定协变量X和z的比例风险模型。我们表明,对事件指标D、累积基线风险H0(T)和其他协变量z进行逻辑或线性回归是推算二元或正态X的合适模型。这个结果在单个二元协变量的情况下是准确的;在其他情况下,它对小协变量效应和/或小累积发生率近似有效。如果我们不知道H0(T),我们用H(T)的Nelson-Aalen估计器来近似它,或者用Cox回归来估计它。我们用模拟研究比较了这两种方法。我们发现,使用log T偏差协变量结果关联趋于零,而新方法具有较低的偏差。总的来说,我们建议在估算模型中加入事件指标和H(T)的Nelson-Aalen估计量。版权所有©2009 John Wiley & Sons, Ltd
Multiple imputation is commonly used to impute missing data, and is typically more efficient than complete cases analysis in regression analysis when covariates have missing values. Imputation may be performed using a regression model for the incomplete covariates on other covariates and, importantly, on the outcome. With a survival outcome, it is a common practice to use the event indicator D and the log of the observed event or censoring time T in the imputation model, but the rationale is not clear. We assume that the survival outcome follows a proportional hazards model given covariates X and Z. We show that a suitable model for imputing binary or Normal X is a logistic or linear regression on the event indicator D, the cumulative baseline hazard H0(T), and the other covariates Z. This result is exact in the case of a single binary covariate; in other cases, it is approximately valid for small covariate effects and/or small cumulative incidence. If we do not know H0(T), we approximate it by the Nelson–Aalen estimator of H(T) or estimate it by Cox regression. We compare the methods using simulation studies. We find that using log T biases covariate-outcome associations towards the null, while the new methods have lower bias. Overall, we recommend including the event indicator and the Nelson–Aalen estimator of H(T) in the imputation model. Copyright © 2009 John Wiley & Sons, Ltd.
DOI: 10.1177/1536867x0500500204
发表时间: 2005-01-01
期刊: STATA JOURNAL
影响因子: 4.8
作者:
Royston, P
通讯作者: Royston, P
DOI: 10.2307/2289225
发表时间: 1986-06-01
影响因子: 3.7
作者:
RUBIN, DB;SCHENKER, N
通讯作者: SCHENKER, N
DOI: 10.1093/aje/kwh175
发表时间: 2004-07-01
影响因子: 5
作者:
Barzi, F;Woodward, M
通讯作者: Woodward, M
DOI: 10.2307/1391878
发表时间: 1988-07-01
影响因子: 3
作者:
LITTLE, RJA
通讯作者: LITTLE, RJA
DOI: 10.2307/2290525
发表时间: 1991-12-01
影响因子: 3.7
作者:
LI, KH;RAGHUNATHAN, TE;RUBIN, DB
通讯作者: RUBIN, DB