郑英杰,蔡倩莹,范伟,张淼.因果思维在效应估计若干问题中的应用[J].Chinese journal of Epidemiology,2019,40(10):1314-1323 |
因果思维在效应估计若干问题中的应用 |
The application of causal thinking in several issues in estimation of effects |
Received:May 14, 2019 |
DOI:10.3760/cma.j.issn.0254-6450.2019.10.026 |
KeyWord: 因果思维 因果推断 流行病学 效应估计 研究设计 |
English Key Word: Causal thinking Causal inference Epidemiology Effect estimation Study design |
FundProject:国家自然科学基金(81373065,81773490);国家重点研发计划(2017YFC1200203) |
Author Name | Affiliation | E-mail | Zheng Yingjie | Department of Epidemiology, Key Laboratory for Health Technology Assessment, National Commission of Health and Family Planning, Key Laboratory of Public Health Safety, Ministry of Education, School of Public Health, Fudan University, Shanghai 200032, China | yjzheng@fudan.edu.cn | Cai Qianying | Department of Epidemiology, Key Laboratory for Health Technology Assessment, National Commission of Health and Family Planning, Key Laboratory of Public Health Safety, Ministry of Education, School of Public Health, Fudan University, Shanghai 200032, China | | Fan Wei | Department of Epidemiology, Key Laboratory for Health Technology Assessment, National Commission of Health and Family Planning, Key Laboratory of Public Health Safety, Ministry of Education, School of Public Health, Fudan University, Shanghai 200032, China | | Zhang Miao | Department of Epidemiology, Key Laboratory for Health Technology Assessment, National Commission of Health and Family Planning, Key Laboratory of Public Health Safety, Ministry of Education, School of Public Health, Fudan University, Shanghai 200032, China | |
|
Hits: 3185 |
Download times: 1455 |
Abstract: |
流行病学是研究同质群体中“异乎寻常”的现象及其发生原因的一门科学。本文以因果思维结合其图形工具——有向无环图,围绕效应估计的若干问题——效应与关联的关系、变量及其测量版间的时序关系、动态人群自然图景、易感人群的形成、研究人群的选择、协变量和病例类型对效应估计的影响等方面,考察这种思维如何帮助我们重新认识流行病学理论、方法及应用。应加强对因果思维的认识。 |
English Abstract: |
Epidemiology is a branch of science that mainly involves in the etiology studies of non-randomness phenomenon among homogenous populations. In this paper, we use causal-thinking,supported by its tool-Directed Acyclic Graphs, to illustrate how the estimation of effects is affected by the issues as relations between effect and association, time sequences between variables and their measured counterparts, natural picture of dynamic population, formation of susceptible population, selection of study population, impact of covariates and types of cases etc., on the estimation of effects. This type of thinking may help us to re-capture the epidemiological theories, methods and related applications. Thus, causal-thinking should be strengthened. |
View Fulltext
Html FullText
View/Add Comment Download reader |
Close |
|
|
|