基于病例队列设计的平均处理效应的估计  

Estimation of Average Treatment Effect with Case-cohort Design

作　　者：曹永秀[1] 余吉昌 Yong Xiu CAO;Ji Chang YU(School of Statistics and Mathematics,Zhongnan University of Economics and Law,Wuhan 430073,P.R.China)

机构地区：[1]中南财经政法大学统计与数学学院,武汉430073

出　　处：《数学学报（中文版）》2022年第4期751-762,共12页Acta Mathematica Sinica：Chinese Series

基　　金：国家自然科学基金资助项目(11701571);中央高校基本科研基金(31512111206)。

摘　　要：病例队列设计因为具有成本效益而被广泛应用于流行病学和生物医学的研究中.对于病例队列设计,现有的统计方法主要集中在如何得到回归参数的相合及有效的估计上,然而很少有工作估计非随机化处理的因果效应.本文基于病例队列设计数据提出了一种有效的估计平均处理效应的方法,建立了所提估计量的相合性和渐近正态性,并通过仿真研究考察了其在有限样本下的表现.最后,我们将所提方法应用于真实数据的分析中.The case-cohort design has been widely used in epidemiological and biomedical studies due to its cost-effectiveness.Existing statistical methods are primarily focused on obtaining consistent and efficient estimators for the regression parameters.However,there is little work to estimate the causal effect of a nonrandomized treatment on the outcome.In this article,we develop an efficient inference procedure to estimate the average treatment effect based on data from the case-cohort design.We also establish the consistency and asymptotic normality of the proposed estimator.The finite sample performance of the proposed estimator is evaluated through simulation studies.Finally,we use the proposed method to analyze a real data set.

关 键 词：平均处理效应 病例队列设计 Kaplan-Meier估计 观测性研究 倾向得分 

分 类 号：O212.2[理学—概率论与数理统计]