Quantifying Biases in Causal Models: Classical Confounding vs Collider-Stratification Bias
- 1 May 2003
- journal article
- research article
- Published by Ovid Technologies (Wolters Kluwer Health) in Epidemiology
- Vol. 14 (3), 300-306
- https://doi.org/10.1097/01.ede.0000042804.12056.6c
Abstract
It has long been known that stratifying on variables affected by the study exposure can create selection bias. More recently it has been shown that stratifying on a variable that precedes exposure and disease can induce confounding, even if there is no confounding in the unstratified (crude) estimate. This paper examines the relative magnitudes of these biases under some simple causal models in which the stratification variable is graphically depicted as a collider (a variable directly affected by two or more other variables in the graph). The results suggest that bias from stratifying on variables affected by exposure and disease may often be comparable in size with bias from classical confounding (bias from failing to stratify on a common cause of exposure and disease), whereas other biases from collider stratification may tend to be much smaller.Keywords
This publication has 22 references indexed in Scilit:
- An overview of relations among causal modelling methodsInternational Journal of Epidemiology, 2002
- Fallibility in estimating direct effects.International Journal of Epidemiology, 2002
- Causal Knowledge as a Prerequisite for Confounding Evaluation: An Application to Birth Defects EpidemiologyAmerican Journal of Epidemiology, 2002
- Data, Design, and Background Knowledge in Etiologic InferenceEpidemiology, 2001
- Assessment of Structured Socioeconomic Effects on HealthEpidemiology, 2001
- Confounding and Collapsibility in Causal InferenceStatistical Science, 1999
- Causal Diagrams for Epidemiologic ResearchEpidemiology, 1999
- Causal diagrams for empirical researchBiometrika, 1995
- Correcting a Bias?The New England Journal of Medicine, 1978
- Alternative Analytic Methods for Case-Control Studies of Estrogens and Endometrial CancerThe New England Journal of Medicine, 1978