Propensity score weighting with multilevel data.

Propensity score weighting with multilevel data.
复制标题

DOI:
10.1002/sim.5786
复制
发表时间:
2013-08-30
影响因子:
2
通讯作者:
Landrum, Mary Beth
Landrum, Mary Beth
中科院分区:
医学3区
文献类型:
--
作者:
Li, Fan;Zaslavsky, Alan M.;Landrum, Mary Beth

文献摘要

参考文献

被引文献

相似文献

倾向评分方法越来越多地被用作传统回归的参数较少的替代方法,以平衡在描述性和因果比较中观察到的各组差异。在许多学科中收集的数据通常具有分析相关的多级或聚类结构。然而,倾向评分是开发出来的,主要用于非结构化数据。我们提出并比较了几种聚类数据的倾向分数加权估计,包括边际估计、聚类加权估计和双稳健估计。使用分析推导和蒙特卡罗模拟,我们说明了偏见时,通常的假设倾向得分分析不适用于多层次数据。我们发现,利用多层次结构,无论是参数或非参数,在至少一个阶段的倾向评分分析可以大大减少这些偏见。这些方法适用于研究的种族差异,在乳腺癌筛查受益人在医疗保险健康计划。
Propensity score methods are being increasingly used as a less parametric alternative to traditional regression to balance observed differences across groups in both descriptive and causal comparisons. Data collected in many disciplines often have analytically relevant multilevel or clustered structure. The propensity score, however, was developed and has been used primarily with unstructured data. We present and compare several propensity-score-weighted estimators for clustered data, including marginal, cluster-weighted and doubly-robust estimators. Using both analytical derivations and Monte Carlo simulations, we illustrate bias arising when the usual assumptions of propensity score analysis do not hold for multilevel data. We show that exploiting the multilevel structure, either parametrically or nonparametrically, in at least one stage of the propensity score analysis can greatly reduce these biases. These methods are applied to a study of racial disparities in breast cancer screening among beneficiaries in Medicare health plans.
DOI: 10.1097/00005650-199305001-00008
发表时间: 1993-05-01
期刊: MEDICAL CARE
影响因子: 3
作者:
GATSONIS, C;NORMAND, SL;MORRIS, C
通讯作者: MORRIS, C
DOI: 10.3102/1076998609359785
发表时间: 2010-10-01
影响因子: 2.4
作者:
Hong, Guanglei
通讯作者: Hong, Guanglei
评估幼儿园保留政策: 多层次观察数据因果推断案例研究
DOI: 10.1198/016214506000000447
发表时间: 2006-09-01
影响因子: 3.7
作者:
Hong, Guanglei;Raudenbush, Stephen W.
通讯作者: Raudenbush, Stephen W.
DOI: 10.2307/1914288
发表时间: 1948-01-01
期刊: ECONOMETRICA
影响因子: 6.1
作者:
Neyman, J.;Scott, Elizabeth L.
通讯作者: Scott, Elizabeth L.
DOI: 10.2307/2288398
发表时间: 1984-01-01
影响因子: 3.7
作者:
ROSENBAUM, PR;RUBIN, DB
通讯作者: RUBIN, DB