The Importance of Making Assumptions in Bias Analysis
- PMID: 34224472
- PMCID: PMC8318561
- DOI: 10.1097/EDE.0000000000001381
The Importance of Making Assumptions in Bias Analysis
Abstract
Quantitative bias analyses allow researchers to adjust for uncontrolled confounding, given specification of certain bias parameters. When researchers are concerned about unknown confounders, plausible values for these bias parameters will be difficult to specify. Ding and VanderWeele developed bounding factor and E-value approaches that require the user to specify only some of the bias parameters. We describe the mathematical meaning of bounding factors and E-values and the plausibility of these methods in an applied context. We encourage researchers to pay particular attention to the assumption made, when using E-values, that the prevalence of the uncontrolled confounder among the exposed is 100% (or, equivalently, the prevalence of the exposure among those without the confounder is 0%). We contrast methods that attempt to bound biases or effects and alternative approaches such as quantitative bias analysis. We provide an example where failure to make this distinction led to erroneous statements. If the primary concern in an analysis is with known but unmeasured potential confounders, then E-values are not needed and may be misleading. In cases where the concern is with unknown confounders, the E-value assumption of an extreme possible prevalence of the confounder limits its practical utility.
Copyright © 2021 The Author(s). Published by Wolters Kluwer Health, Inc.
Figures
![FIGURE 1.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8318561/bin/ede-32-617-g004.gif)
![FIGURE 2.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8318561/bin/ede-32-617-g006.gif)
![FIGURE 3.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8318561/bin/ede-32-617-g009.gif)
Comment in
-
To Bound or Not to Bound: Is That the Question?Epidemiology. 2021 Sep 1;32(5):635-637. doi: 10.1097/EDE.0000000000001379. Epidemiology. 2021. PMID: 34224474 No abstract available.
Similar articles
-
Assessing the impact of unmeasured confounders for credible and reliable real-world evidence.Pharmacoepidemiol Drug Saf. 2020 Oct;29(10):1219-1227. doi: 10.1002/pds.5117. Epub 2020 Sep 14. Pharmacoepidemiol Drug Saf. 2020. PMID: 32929830 Review.
-
[How to adjust confounders in studies on observational comparative effectiveness: (3) approaches on sensitivity analysis for confounder adjustment].Zhonghua Liu Xing Bing Xue Za Zhi. 2019 Dec 10;40(12):1645-1649. doi: 10.3760/cma.j.issn.0254-6450.2019.12.026. Zhonghua Liu Xing Bing Xue Za Zhi. 2019. PMID: 32062931 Chinese.
-
Mediational E-values: Approximate Sensitivity Analysis for Unmeasured Mediator-Outcome Confounding.Epidemiology. 2019 Nov;30(6):835-837. doi: 10.1097/EDE.0000000000001064. Epidemiology. 2019. PMID: 31348008 Free PMC article.
-
Bias Analysis for Uncontrolled Confounding in the Health Sciences.Annu Rev Public Health. 2017 Mar 20;38:23-38. doi: 10.1146/annurev-publhealth-032315-021644. Epub 2017 Jan 6. Annu Rev Public Health. 2017. PMID: 28125388 Review.
-
Sensitivity Analysis Without Assumptions.Epidemiology. 2016 May;27(3):368-77. doi: 10.1097/EDE.0000000000000457. Epidemiology. 2016. PMID: 26841057 Free PMC article.
Cited by
-
Sensitivity analysis for causality in observational studies for regulatory science.J Clin Transl Sci. 2023 Dec 5;7(1):e267. doi: 10.1017/cts.2023.688. eCollection 2023. J Clin Transl Sci. 2023. PMID: 38380390 Free PMC article.
-
Association between trajectories of prescription opioid use and risk of opioid use disorder and overdose among US nonmetastatic breast cancer survivors.Breast Cancer Res Treat. 2024 Apr;204(3):561-577. doi: 10.1007/s10549-023-07205-6. Epub 2024 Jan 8. Breast Cancer Res Treat. 2024. PMID: 38191684
-
Quantitative bias analysis in practice: review of software for regression with unmeasured confounding.BMC Med Res Methodol. 2023 May 4;23(1):111. doi: 10.1186/s12874-023-01906-8. BMC Med Res Methodol. 2023. PMID: 37142961 Free PMC article.
-
Guidelines for Reporting Observational Research in Urology: The Importance of Clear Reference to Causality.Urology. 2023 Jul;177:1-5. doi: 10.1016/j.urology.2023.04.007. Epub 2023 Apr 19. Urology. 2023. PMID: 37085050 Free PMC article. No abstract available.
-
Use of antihypertensive drugs and risk of cutaneous melanoma: a nationwide nested case-control study.Int J Epidemiol. 2023 Jun 6;52(3):887-898. doi: 10.1093/ije/dyac223. Int J Epidemiol. 2023. PMID: 36413027 Free PMC article.
References
-
- Hernán MA, Robins JM. Causal Inference: What If. Chapman & Hall/CRC. 2020.
-
- Bross ID. Pertinency of an extraneous variable. J Chronic Dis. 1967;20:487–495. - PubMed
-
- Cornfield J, Haenszel W, Hammond EC, Lilienfeld AM, Shimkin MB, Wynder EL. Smoking and lung cancer: recent evidence and a discussion of some questions. J Natl Cancer Inst. 1959;22:173–203. - PubMed
-
- Flanders WD, Khoury MJ. Indirect assessment of confounding: graphic description and limits on effect of adjusting for covariates. Epidemiology. 1990;1:239–246. - PubMed
-
- Schlesselman JJ. Assessing effects of confounding variables. Am J Epidemiol. 1978;108:3–8. - PubMed
Publication types
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources