Confounding and Collapsibility in Causal Inference
Greenland, Sander ; Robins, James M. ; Pearl, Judea
Statist. Sci., Tome 14 (1999) no. 1, p. 29-46 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
Consideration of confounding is fundamental to the design and analysis of studies of causal effects. Yet, apart from confounding in experimental designs, the topic is given little or no discussion in most statistics texts. We here provide an overview of confounding and related concepts based on a counterfactual model for causation. Special attention is given to definitions of confounding, problems in control of confounding, the relation of confounding to exchangeability and collapsibility, and the importance of distinguishing confounding from noncollapsibility.
Publié le : 1999-02-14
Classification:  Bias, , , , , , , , , , .,  causation,  collapsibility,  confounding,  contingency tables,  exchangeability,  observational studies,  odds ratio,  relative risk,  risk assessment,  Simpson's paradox 
@article{1009211805,
     author = {Greenland, Sander and Robins, James M. and Pearl, Judea},
     title = {Confounding and Collapsibility in Causal Inference},
     journal = {Statist. Sci.},
     volume = {14},
     number = {1},
     year = {1999},
     pages = { 29-46},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1009211805}
}

Greenland, Sander; Robins, James M.; Pearl, Judea. Confounding and Collapsibility in Causal Inference. Statist. Sci., Tome 14 (1999) no. 1, pp.  29-46. http://gdmltest.u-ga.fr/item/1009211805/