Bias and Confounding
Clinical orthopedic studies can be affected by many forms of bias, including confounding. Any error promoting one outcome over another introduces bias into research. The risk of different types of bias can occur during many phases of research including study design, data collection, and publication. Confounding may affect both the exposure and outcome of a study and may or may not be measurable. For measurable confounding factors, methods of control include randomization, restriction, and matching. While most forms of bias can be minimized through methods such as selecting appropriate study designs and proper control groups, some bias cannot be mitigated.
- 2.Cassel C, Sarndal C, Wretman J. Some uses of statistical models in connection with the nonresponse problem. In: Madow W, Olkin I, editors. Incomplete data in sample surveys, Symposium on incomplete data, proceedings, vol. 3. New York, NY: Academic; 1983.Google Scholar
- 3.Cohen J. Statistical power analysis for the behavioral sciences. 2nd ed. New York: Routledge.Google Scholar
- 8.Flury B, Riedwyl H. Standard distance in univariate and multivariate analysis. Am Stat. 1986;40:249–51.Google Scholar
- 11.Guo S, Fraser M. Propensity score analysis: statistical methods and applications. 2nd ed. Thousand Oaks, CA: Sage; 2015.Google Scholar
- 12.Hennekens C, Buring J. Epidemiology in medicine. 1st ed. Boston: Little, Brown and Company; 1987.Google Scholar
- 14.JBJS. JBJS Inc. Journals Level of Evidence [Internet]. J Bone Joint Surg. 2015. https://journals.lww.com/jbjsjournal/Pages/Journals-Level-of-Evidence.aspx.
- 24.Shapiro S. Causation, bias and confounding: a hitchhiker’s guide to the epidemiological galaxy Part 3: Principles of causality in epidemiological research: statistical stability, dose- and duration-response effects, internal and external consistency, analogy and biological plausibility. J Fam Plann Reprod Health Care. 2008c;34(4):261–4.Google Scholar
- 26.van der Heijden RA, Oei EHG, Bron EE, van Tiel J, van Veldhoven PLJ, Klein S, et al. No difference on quantitative magnetic resonance imaging in patellofemoral cartilage composition between patients with patellofemoral pain and healthy controls. Am J Sports Med. 2016;44(5):1172–8.CrossRefGoogle Scholar
- 27.Viswanathan M, Berkman ND, Dryden DM, Hartling L. Assessing risk of bias and confounding in observational studies of interventions or exposures: further development of the RTI item bank. Agency Healthc Res Qual. 2013:1–22.Google Scholar