首页> 外文OA文献 >Propensity Score Matching and Subclassification in Observational Studies with Multi-level Treatments
【2h】

Propensity Score Matching and Subclassification in Observational Studies with Multi-level Treatments

机译:观察研究中的倾向得分匹配和子分类   多层次治疗

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

In this paper, we develop new methods for estimating average treatmenteffects in observational studies, focusing on settings with more than twotreatment levels under unconfoundedness given pre-treatment variables. Weemphasize subclassification and matching methods which have been found to beeffective in the binary treatment literature and which are among the mostpopular methods in that setting. Whereas the literature has suggested thatthese particular propensity-based methods do not naturally extend to themulti-level treatment case, we show, using the concept of weakunconfoundedness, that adjusting for or matching on a scalar function of thepre-treatment variables removes all biases associated with observedpre-treatment variables. We apply the proposed methods to an analysis of theeffect of treatments for fibromyalgia. We also carry out a simulation study toassess the finite sample performance of the methods relative to previouslyproposed methods.
机译:在本文中,我们开发了一种新的方法来估计观察研究中的平均治疗效果,重点是在给定预处理变量的情况下,在无混淆的情况下设置两个以上的治疗水平。我们强调在二元治疗文献中发现有效的子分类和匹配方法,它们是该背景下最受欢迎的方法之一。尽管文献表明这些基于倾向的特定方法并不能自然地扩展到多级治疗案例,但我们使用弱无混杂性的概念表明,对预处理变量的标量函数进行调整或匹配会消除与变量相关的所有偏差。观察到的预处理变量我们将提出的方法应用于治疗纤维肌痛的疗效分析。我们还进行了仿真研究,以评估该方法相对于先前提出的方法的有限样本性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号