The number of strata in propensity score stratification for a binary outcome
The number of strata in propensity score stratification for a binary outcome
复制标题
二元结果的倾向得分分层中的层数
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
G. Ruxton
中科院分区：
文献类型：
--
作者：
M. Neuhäuser;M. Thielmann;G. Ruxton
前言非干预性和其他观察性研究在医学研究中已变得重要。在此类观察性、非随机研究中，组间通常在某些基线协变量方面存在差异。在这些研究的统计分析中越来越多地使用倾向分数。基于倾向分数的分层，也称为子分类，是可能的方法之一。有五层使用的准标准。在本文中，我们专注于一个二元的结果和评价上述标准的使用五个层次。材料和方法不同数量的地层的偏见和权力进行了研究与模拟研究。该方法说明了使用数据从一项研究中，糖尿病和三支血管疾病的患者进行冠状动脉搭桥术与以前的经皮冠状动脉介入治疗进行了比较。结果我们表明，超过五个层次可以更强大，并给出更少的偏见的结果。然而，使用超过十层几乎没有任何进一步的好处。结论当应用分层时，超过5层可能是优选的，特别是因为增加了功率。我们的模拟研究并没有显示出一个明确的赢家，因此一个有用的策略可能是与五个以及与十个层次。
Introduction Non-interventional and other observational studies have become important in medical research. In such observational, non-randomized studies, groups usually differ in some baseline covariates. Propensity scores are increasingly being used in the statistical analysis of these studies. Stratification, also called subclassification, based on propensity scores is one of the possible methods. There is the quasi-standard of using five strata. In this paper we focus on a binary outcome and evaluate the above-mentioned standard of using five strata. Material and methods Bias and power for different numbers of strata are investigated with a simulation study. The methods are illustrated using data from a study where patients with diabetes mellitus and triple vessel disease undergoing coronary artery bypass surgery with and without previous percutaneous coronary intervention were compared. Results We show that more than five strata can be more powerful and give less biased results. However, using more than ten strata hardly gives any further benefit. Conclusions When applying a stratification, more than five strata may be preferable, especially because of increased power. Our simulation study does not show a clear winner; hence a useful strategy could be to work with five as well as with ten strata.