How to Understand Measures of Effect in Clinical Research: Practical interpretation and Application
DOI:
https://doi.org/10.35434/rcmhnaaa.2023.161.1935Keywords:
Measures of Association, Relative Risk, Prevalence Ratio, Odds Ratio, Hazard RatioAbstract
In clinical research, assessing the association between two variables is a critical and fundamental task. Clinical studies aim to establish the effect size of the exposure to a variable on a given outcome. To measure this effect size, various statistical measures are used, among the most common are the prevalence ratio (PR), the relative risk (RR), the odds ratio (OR), the hazard ratio (HR), the incidence rate ratio (IRR), the attributable risk (AR), the number needed to treat (NNT), the mean difference (MD), and the linear regression coefficient (β). Each of these measures has its advantages and limitations, and their choice depends on the type of study and the nature of the data being analyzed. Therefore, it is important to understand the interpretation and use of each of them to perform an appropriate analysis. In this article, our goal is to explain in a practical way how to interpret these measures and how to use their p-values and 95% confidence intervals to assess statistical inference. Understanding how to evaluate the association between two variables is crucial for the design and analysis of high-quality clinical studies. This enables evidence-based decision-making and promotes improvements in patient care.
Downloads
Metrics
References
World Health Organization. The WHO strategy on research for health [Internet]. Geneva: World Health Organization. 2020 [cited 2023 mar 10] Available from: https://www.who.int/publications-detail-redirect/9789241503259
Barboza-Palomino M, Caycho T, Castilla-Cabello H. Políticas públicas en salud basadas en la evidencia. Discusión en el contexto peruano. Salud Publica Mex. 2017;59(1):2. doi:10.21149/7881
González-Ramírez AR, Rivas-Ruiz F. Measures of frequency, magnitude of association and impact in epidemiology. Allergologia et Immunopathologia. 2010;38(3):147-152. doi:10.1016/j.aller.2010.02.002
Celentano DD, Szklo M, Gordis L. Gordis Epidemiology. 6th edition. Elsevier; 2019.
Goodwin G, Ryu SY. Understanding The Odds: Statistics in Public Health. Front Young Minds. 2023;10:926624. doi:10.3389/frym.2022.926624
Szumilas M. Explaining odds ratios. J Can Acad Child Adolesc Psychiatry [Internet]. 2010 [cited 2023 mar 13];19(3):227-229. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2938757/.
Knol MJ, Le Cessie S, Algra A, Vandenbroucke JP, Groenwold RHH. Overestimation of risk ratios by odds ratios in trials and cohort studies: alternatives to logistic regression. CMAJ. 2012;184(8):895-9. doi:10.1503/cmaj.101715
Hoffman JIE. Chapter 35 - Survival Analysis. In: Hoffman JIE, ed. Basic Biostatistics for Medical and Biomedical Practitioners (Second Edition). Academic Press. 2019:599-619. doi:10.1016/B978-0-12-817084-7.00035-8
Barraclough H, Simms L, Govindan R. Biostatistics Primer: What a Clinician Ought to Know: Hazard Ratios. Journal of Thoracic Oncology. 2011;6(6):978-82. doi:10.1097/JTO.0b013e31821b10ab
Barros AJ, Hirakata VN. Alternatives for logistic regression in cross-sectional studies: an empirical comparison of models that directly estimate the prevalence ratio. BMC Med Res Methodol. 2003;3(1):21. doi:10.1186/1471-2288-3-21
Grant RL. Converting an odds ratio to a range of plausible relative risks for better communication of research findings. BMJ. 2014:348:f7450. doi: 10.1136/bmj.f7450
Guyatt GH, Oxman AD, Kunz R, et al. GRADE guidelines 6. Rating the quality of evidence—imprecision. Journal of Clinical Epidemiology. 2011;64(12):1283-93. doi:10.1016/j.jclinepi.2011.01.012
Newcombe RG, Bender R. Implementing GRADE: calculating the risk difference from the baseline risk and the relative risk. Evid Based Med. 2014;19(1):6-8. doi:10.1136/eb-2013-101340
Coughlin S, Benichou J, Weed D. Estimación del riesgo atribuible en los estudios de casos y controles. Bol Oficina Saint Panam [Internet]. 1996 [citado 10 mar 2023];12(2):143-153. Disponible en: https://iris.paho.org/bitstream/handle/10665.2/15445/v121n2p143.pdf?sequence=
Citrome L, Ketter TA. When does a difference make a difference? Interpretation of number needed to treat, number needed to harm, and likelihood to be helped or harmed. Int J Clin Pract. 2013;67(5):407-11. doi:10.1111/ijcp.12142
Hutton JL. Number needed to treat and number needed to harm are not the best way to report and assess the results of randomised clinical trials. British Journal of Haematology. 2009;146(1):27-30. doi:10.1111/j.1365-2141.2009.07707.x
Quertemont E. How to Statistically Show the Absence of an Effect. Psychol Belg. 2011;51(2):109. doi:10.5334/pb-51-2-109
Daniel WW, Cross CL. Biostatistics: A Foundation for Analysis in the Health Sciences. Eleventh edition. Wiley; 2019.
Phillips MR, Wykoff CC, Thabane L, et al. The clinician’s guide to p values, confidence intervals, and magnitude of effects. Eye. 2022;36(2):341-2. doi:10.1038/s41433-021-01863-w
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2023 Jessica Hanae Zafra-Tanaka, Alvaro Taype-Rondan, Daniel Fernandez-Guzman
This work is licensed under a Creative Commons Attribution 4.0 International License.
