A structural classification of strategies for confounding control in research design.
10.3760/cma.j.issn.0254-6450.2018.07.025
- Author:
Y N HE
1
,
2
;
L L LIU
3
;
Q Y CAI
3
;
N Q ZHAO
4
;
Y J ZHENG
1
,
5
,
6
Author Information
1. Department of Public Health Microbiology, School of Public Health, Fudan University, Shanghai 200032, China
2. Department of Epidemiology, School of Public Health, Fudan University, Shanghai 200032, China.
3. Department of Public Health Microbiology, School of Public Health, Fudan University, Shanghai 200032, China.
4. Department of Biostatistics, School of Public Health, Fudan University, Shanghai 200032, China.
5. Key Laboratory of Public Health Safety, Ministry of Education, School of Public Health, Fudan University, Shanghai 200032, China
6. Key Laboratory for Health Technology Assessment, National Commission of Health and Family Planning, School of Public Health, Fudan University, Shanghai 200032, China.
- Publication Type:Journal Article
- Keywords:
Causality;
Confounding control;
Directed Acyclic Graphs;
Research designs
- MeSH:
Causality;
Confounding Factors, Epidemiologic;
Humans;
Models, Statistical;
Random Allocation;
Randomized Controlled Trials as Topic;
Research Design
- From:
Chinese Journal of Epidemiology
2018;39(7):999-1002
- CountryChina
- Language:Chinese
-
Abstract:
Confounding affects the causal relation among the population. Depending on whether the confounders are known, measurable or measured, they can be divided into four categories. Based on Directed Acyclic Graphs, the strategies for confounding control can be classified as (1) the broken-confounding-path method, which can be further divided into single and dual broken paths, corresponding to exposure complete intervention, restriction and stratification, (2) and the reserved-confounding-path method, which can be further divided into incomplete exposure intervention (in instrumental variable design and non-perfect random control test), mediator method and matching method. Among them, random control test, instrumental variable design or Mendelian randomized design, mediator method can meet the requirements for controlling all four types of confounders, while the restriction, stratification and matching methods are only applicable to known, measurable and measured confounders. Identifying the mechanisms of confounding control is a prerequisite for obtaining correct causal effect estimates, which will be helpful in research design.
