Identifiability, exchangeability, and epidemiological confounding
- PMID: 3771081
- DOI: 10.1093/ije/15.3.413
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 collapsibility-based definitions.
Similar articles
-
Summary of relationships between exchangeability, biasing paths and bias.Eur J Epidemiol. 2015 Oct;30(10):1089-99. doi: 10.1007/s10654-014-9915-2. Epub 2014 Jun 4. Eur J Epidemiol. 2015. PMID: 24894825 Review.
-
Confounding in health research.Annu Rev Public Health. 2001;22:189-212. doi: 10.1146/annurev.publhealth.22.1.189. Annu Rev Public Health. 2001. PMID: 11274518 Review.
-
Covariate balance for no confounding in the sufficient-cause model.Ann Epidemiol. 2018 Jan;28(1):48-53.e2. doi: 10.1016/j.annepidem.2017.11.005. Epub 2017 Nov 23. Ann Epidemiol. 2018. PMID: 29241736
-
Negative Control Exposures: Causal Effect Identifiability and Use in Probabilistic-bias and Bayesian Analyses With Unmeasured Confounders.Epidemiology. 2022 Nov 1;33(6):832-839. doi: 10.1097/EDE.0000000000001528. Epub 2022 Jul 27. Epidemiology. 2022. PMID: 35895515 Free PMC article.
-
Identifiability, exchangeability and confounding revisited.Epidemiol Perspect Innov. 2009 Sep 4;6:4. doi: 10.1186/1742-5573-6-4. Epidemiol Perspect Innov. 2009. PMID: 19732410 Free PMC article.
Cited by
-
Smoking cessation and survival among people diagnosed with non-metastatic cancer.BMC Cancer. 2020 Aug 5;20(1):726. doi: 10.1186/s12885-020-07213-5. BMC Cancer. 2020. PMID: 32758159 Free PMC article.
-
Antecedents and mediators of physical activity in endometrial cancer survivors: Increasing physical activity through steps to health.Health Psychol. 2015 Oct;34(10):1022-32. doi: 10.1037/hea0000188. Epub 2015 Feb 2. Health Psychol. 2015. PMID: 25642840 Free PMC article.
-
Inflammatory Pathways in Overweight and Obese Persons as a Potential Mechanism for Cognitive Impairment and Earlier Onset Alzeihmer's Dementia in the General Population: A Narrative Review.Biomedicines. 2023 Dec 6;11(12):3233. doi: 10.3390/biomedicines11123233. Biomedicines. 2023. PMID: 38137454 Free PMC article. Review.
-
The complex relationship between CD4 count, HIV viral load, trimethoprim-sulfamethoxazole prophylaxis, and skin-and-soft-tissue infection risk in patients with HIV: insights from a causal diagram and simulation study.Epidemiol Infect. 2016 Oct;144(13):2889-98. doi: 10.1017/S0950268816000789. Epub 2016 May 4. Epidemiol Infect. 2016. PMID: 27143243 Free PMC article.
-
An introduction to causal inference.Int J Biostat. 2010 Feb 26;6(2):Article 7. doi: 10.2202/1557-4679.1203. Int J Biostat. 2010. PMID: 20305706 Free PMC article. Review.
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical