On the estimation and use of propensity scores in case-control and case-cohort studies
On the estimation and use of propensity scores in case-control and case-cohort studies
复制标题
DOI：
10.1093/aje/kwm069
复制
发表时间：
2007-08-01
影响因子：
5
通讯作者：
Hennessy, Sean
中科院分区：
文献类型：
--
作者：
Mansson, Roger;Joffe, Marshall M.;Hennessy, Sean
在队列研究中，使用倾向评分来调整测量的混杂因素已变得越来越流行。然而，它们在病例对照和病例队列研究中的应用却很少受到关注。作者提出了一些理论的估计和使用的倾向分数的病例对照和病例队列研究，并提出了模拟研究的结果，研究是否实现了大样本的期望，在典型规模的研究。倾向评分在病例对照和病例队列研究中的应用不如队列研究直接。作者的模拟揭示了两个潜在的重要问题。首先，当使用几种潜在的方法时，倾向评分水平对比值比有人为影响。这种现象的幅度随着样本量的增加而减小。其次，几种潜在的方法产生的估计倾向分数不收敛到真实值的样本量增加，因此，可能无法完全调整测量的混杂因素。然而，在我们的模拟中，残余混杂的程度似乎不大。考虑在病例对照或病例队列研究中使用倾向评分的研究人员应考虑人为效应修改的可能性及其控制潜在混杂因素的能力降低。
The use of propensity scores to adjust for measured confounding factors has become increasingly popular in cohort studies. However, their use in case-control and case-cohort studies has received little attention. The authors present some theory on the estimation and use of propensity scores in case-control and case-cohort studies and present the results of simulation studies that examine whether large-sample expectations are realized in studies of typical size. The application of propensity scores is less straightforward in case-control and case-cohort studies than in cohort studies. The authors' simulations revealed two potentially important issues. First, when using several potential approaches, there is artifactual effect modification of the odds ratio by level of propensity score. The magnitude of this phenomenon decreases as the sample size increases. Second, several potential approaches produce estimated propensity scores that do not converge to the true value as sample size increases and, thus, can fail to adjust fully for measured confounding factors. However, the magnitude of residual confounding appeared modest in our simulations. Researchers considering using propensity scores in case-control or case-cohort studies should consider the potential for artifactual effect modification and their reduced ability to control for potential confounding factors.