随机抽样:因果视角  

Random sampling:a causal perspective

作　　者：牟育彤 郭阳 李青 张淼 索晨 李亚欣 刘海燕 胡安群 郑英杰 MU Yutong;GUO Yang;LI Qing;ZHANG Miao;SUO Chen;LI Yaxin;LIU Haiyan;HU Anqun;ZHENG Yingjie(Department of Epidemiology,Key Laboratory for Health Technology Assessment,National Health Commission of the people′s Republic of China,School of Public Health,Fudan University,Shanghai 200032,China;Peking University Shenzhen Hospital,Shenzhen Peking University-The Hong Kong University of Science and Technology Medical Center,Shenzhen 518036,China;Affiliated Anqing Hospi-tal of Anhui Medical University,Anqing Municipal Hospital,Anqing 246003,China)

机构地区：[1]复旦大学公共卫生学院流行病学教研室,国家卫生健康委员会卫生技术评估重点实验室(复旦大学),上海200032 [2]北京大学深圳医院,深圳北京大学香港科技大学医学中心,深圳518036 [3]安徽医科大学附属安庆医院,安庆市立医院,安庆246003

出　　处：《中华疾病控制杂志》2023年第8期989-992,共4页Chinese Journal of Disease Control & Prevention

基　　金：国家自然科学基金(82173582,81373065,81773490)。

摘　　要：本研究从因果图和因果模型的角度解释了简单随机抽样、整群抽样和分层抽样的结构和原理,清晰呈现了抽样偏倚的产生和调整过程。发现当研究的目标属性与是否抽中有关联时,样本对总体的代表性将产生偏差,即抽样偏倚或抽样的系统误差。整群抽样和分层抽样是两种对抽样偏倚的不同调整策略;前者找到一个目标无关变量作为分群变量,而后者直接调整了引起抽样偏倚且与研究属性关联的变量。在抽样方法的选择上,整群抽样要求群内异质且群间同质,分层抽样则正好相反。最后,本研究为实际研究工作中对抽样方法的选择提供了路线参考,可帮助读者提高对随机抽样的认识,考量研究方法的选择。This article explained the structure and principle of simple random sampling,cluster sampling,and stratification sampling from the perspective of causal graphs.The process of generation and adjustment of sampling bias was clearly presented.We found that:when the target attribute of the study was related to other attributes which affected the selection of the samples,the representative of the sample would be biased.In other words,the sampling bias or the systematic error of sampling would appear.When selecting sampling methods,cluster sampling requires heterogeneity within clusters but homogeneity among clusters.In contrast,stratified sampling requires the opposite way.Finally,this paper provides a route for the selection of sampling methods in practical research work,which can help readers to improve the acknowledgment of random sampling and consider the best sampling method.

关 键 词：抽样 因果图 抽样偏倚 分层抽样 整群抽样 

分 类 号：R780.1[医药卫生—口腔医学] R543.4[医药卫生—临床医学]