Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Identifiability, Exchangeability, and Epidemiological Confounding

Identifiability, Exchangeability, and Epidemiological Confounding Abstract Non-identifiability of parameters is a well-recognized problem in classical statistics, and Bayesian statisticians have long recognized the importance of exchangeability assumptions in making statistical Inferences. A seemingly unrelated problem in epidemiology is that of confounding: bias in estimation of the effects of an exposure on disease risk, due to inherent differences in risk between exposed and unexposed individuals. Using a simple deterministic model for exposure effects, a logical connection is drawn between the concepts of identifiability, exchangeability, and confounding. This connection allows one to view the problem of confounding as arising from problems of identifiability, and reveals the exchangeability assumptions that are implicit in confounder control methods. It also provides further justification for confounder definitions based on comparability of exposure groups, as opposed to coHapsJbility-based definitions. This content is only available as a PDF. © International Epidemioloical Association http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Epidemiology Oxford University Press

Identifiability, Exchangeability, and Epidemiological Confounding

Loading next page...
 
/lp/oxford-university-press/identifiability-exchangeability-and-epidemiological-confounding-AmPKvej0Yu

References (16)

Publisher
Oxford University Press
Copyright
© International Epidemioloical Association
ISSN
0300-5771
eISSN
1464-3685
DOI
10.1093/ije/15.3.413
Publisher site
See Article on Publisher Site

Abstract

Abstract Non-identifiability of parameters is a well-recognized problem in classical statistics, and Bayesian statisticians have long recognized the importance of exchangeability assumptions in making statistical Inferences. A seemingly unrelated problem in epidemiology is that of confounding: bias in estimation of the effects of an exposure on disease risk, due to inherent differences in risk between exposed and unexposed individuals. Using a simple deterministic model for exposure effects, a logical connection is drawn between the concepts of identifiability, exchangeability, and confounding. This connection allows one to view the problem of confounding as arising from problems of identifiability, and reveals the exchangeability assumptions that are implicit in confounder control methods. It also provides further justification for confounder definitions based on comparability of exposure groups, as opposed to coHapsJbility-based definitions. This content is only available as a PDF. © International Epidemioloical Association

Journal

International Journal of EpidemiologyOxford University Press

Published: Sep 1, 1986

There are no references for this article.