ORIGINAL ARTICLE
Relative risks and odds ratios: Simple rules on when and how to use them
Dean P. McKenzie,
Christopher Thomas,
Corresponding Author
Dean P. McKenzie
Epworth HealthCare, Melbourne, Australia
Department of Statistics, Data Science and Epidemiology, Swinburne University of Technology, Melbourne, Australia
Correspondence
Dean McKenzie, Epworth HealthCare, Melbourne, Australia.
Email: [email protected]
Search for more papers by this authorDean P. McKenzie,
Christopher Thomas,
Corresponding Author
Dean P. McKenzie
Epworth HealthCare, Melbourne, Australia
Department of Statistics, Data Science and Epidemiology, Swinburne University of Technology, Melbourne, Australia
Correspondence
Dean McKenzie, Epworth HealthCare, Melbourne, Australia.
Email: [email protected]
Search for more papers by this authorAbstract
Aim
Relative risks and odds ratios are widely reported in the medical literature, but can be very difficult to understand. We sought to further clarify these important indices.
Methods
We illustrated both relative risks and odds ratios using bar charts, then looked at the types of study for which each statistic is suited. We demonstrated calculation of relative risks and odds ratios through analysis of tabled data from a recent published longitudinal study, using a 2 × 2 table and R, the open-source statistical programming language. Simple rules for when and how to use relative risks and odds ratios are presented.
Conclusion
Understanding the difference between relative risks and odds ratios and when and how to use them may aid clinical interpretation, dissemination and translation of research findings.
CONFLICT OF INTEREST
None.
REFERENCES
- 1Ioannidis JPA, Stuart ME, Brownlee S, Strite SA. How to survive the medical misinformation mess. Eur J Clin Invest. 2017; 47(11): 795-802.
- 2van Koeverden ID, den Ruijter HM, Scholtes VPW, et al. A single preoperative blood test predicts postoperative sepsis and pneumonia after coronary bypass or open aneurysm surgery. Eur J Clin Invest. 2019; 49(3):e13055.
- 3Last A, Wilson S. Relative risks and odds ratios: what's the difference? J Fam Pract. 2004; 53(2): 108.
- 4Persoskie A, Ferrer RA. A most odd ratio: interpreting and describing odds ratios. Am J Prev Med. 2017; 52(2): 224-228.
- 5Schmidt CO, Kohlmann T. When to use the odds ratio or the relative risk? Int J Public Health. 2008; 53(3): 165-167.
- 6Spiegelhalter D. The Art of Statistics: Learning from Data. London: Pelican; 2019.
- 7A'Court C, Stevens R, Heneghan C. Against all odds? Improving the understanding of risk reporting. Br J Gen Pract. 2012; 62(596): e220-223.
- 8Riedel MG. Odds & Chances for Kids: A Look at Probability. New York: Prentice-Hall; 1979.
- 9Mazur J. What's Luck Got To do With it? The History, Mathematics and Psychology of the Gambler's Illusion. Princeton, NJ: Princeton University Press; 2010.
10.1515/9781400834457 Google Scholar
- 10Stewart I. Significant Figures: Lives and Works of Trailblazing Mathematicians. London: Profile; 2017.
- 11Wilber ST, Fu R. Risk ratios and odds ratios for common events in cross-sectional and cohort studies. Acad Emerg Med. 2010; 17(6): 649-651.
- 12Katz MH. Study Design and Statistical Analysis: A Practical Guide for Clinicians. New York: Cambridge University Press; 2006.
10.1017/CBO9780511616761 Google Scholar
- 13Ponsford J, Nguyen S, Downing M, et al. Factors associated with persistent post-concussion symptoms following mild traumatic brain injury in adults. J Rehabil Med. 2019; 51(1): 32-39.
- 14McNeil JJ, Nelson MR, Woods RL, et al. Effect of aspirin on all-cause mortality in the healthy elderly. N Engl J Med. 2018; 379(16): 1519-1528.
- 15Grimes DA. "Case-control" confusion: mislabeled reports in obstetrics and gynecology journals. Obstet Gynecol. 2009; 114(6): 1284-1286.
- 16Sultana RV, McKenzie DP, Fahey MT, Sutherland M, Nimorakiotakis V. Beta-blocker use is an independent risk factor for thunderstorm asthma. Emerg Med Australas. 2019; 31(6): 955-960.
- 17Zammit S, Allebeck P, Andreasson S, Lundberg I, Lewis G. Self reported cannabis use as a risk factor for schizophrenia in Swedish conscripts of 1969: historical cohort study. BMJ. 2002; 325(7374): 1199.
- 18Tamhane AR, Westfall OR, Burkholder GA, Cutter GR. Prevalence odds ratio versus prevalence ratio: choice comes with consequences. Stat Med. 2016; 35(30): 5730-5735.
- 19Guerrero-Romero F, Rodriguez-Moran M. The ratio potassium-to-magnesium intake and high blood pressure. Eur J Clin Invest. 2019; 49(6):e13093.
- 20Gonzales TK, Yonker JA, Chang V, Roan CL, Herd P, Atwood CS. Myocardial infarction in the Wisconsin Longitudinal Study: the interaction among environmental, health, social, behavioural and genetic factors. BMJ Open. 2017; 7(1):e011529.
- 21Masarwa R, Platt RW, Filion KB. Acetaminophen use during pregnancy and the risk of attention deficit hyperactivity disorder: a causal association or bias? Paediatr Perinat Epidemiol. 2020. SPECIALISSUE:ACETAMINOPHIN-NEURODEVELOPMENT. https://doi.org/10.1111/ppe.12615
- 22Greenland S, Robins J. Identifiablity, exchangeability and confounding revisited. Epidemiol Perspect Innov. 2009; 6: 4.
- 23Pearl J, Mackenzie D. The Book of Why: The New Science of Cause and Effect. New York: Basic Books; 2018.
- 24Williamson EJ, Aitken Z, Lawrie J, Dharmage SC, Burgess JA, Forbes AB. Introduction to causal diagrams for confounder selection. Respirology. 2014; 19(3): 303-311.
- 25Hosmer DW, Lemeshow S, Sturdivant RX. Applied Logistic Regression, 3rd edn. Hoboken, New Jersey: Wiley; 2013.
- 26Richardson AM, Joshy G, D'Este CA. Understanding statistical principles in linear and logistic regression. Med J Aust. 2018; 208(8): 332-334.
- 27Ikin JF, McKenzie DP, Gwini SM, et al. Major depression and depressive symptoms in Australian Gulf War veterans 20 years after the Gulf War. J Affect Disord. 2016; 189: 77-84.
- 28Zou G. A modified Poisson regression approach to prospective studies with binary data. Am J Epidemiol. 2004; 159(7): 702-706.
- 29Ben-Shlomo Y, Collin SM, Quekett J, Sterne JA, Whiting P. Presentation of diagnostic information to doctors may change their interpretation and clinical management: a web-based randomised controlled trial. PLoS ONE. 2015; 10(7):e0128637.
- 30Bruckmaier G, Binder K, Krauss S, Kufner HM. An eye-tracking study of statistical reasoning with tree diagrams and 2 x 2 tables. Front Psychol. 2019; 10: 632.
- 31Gigerenzer G. Risk Savvy. How to Make Good Decisions. London: Penguin; 2014.
- 32Emery JD, Pirotta M, Macrae F, et al. 'Why don't I need a colonoscopy?' A novel approach to communicating risks and benefits of colorectal cancer screening. Aust J Gen Pract. 2018; 47(6): 343-349.
- 33McDowell M, Gigerenzer G, Wegwarth O, Rebitschek FG. Effect of tabular and Icon fact box formats on comprehension of benefits and harms of prostate cancer screening: a randomized trial. Med Decis Making. 2019; 39(1): 41-56.
- 34McKenzie DP, Sim MR, Clarke DM, Forbes AB, Ikin JF, Kelsall HL. Developing a brief depression screen and identifying associations with comorbid physical and psychological illness in Australian Gulf War veterans. J Psychosom Res. 2015; 79(6): 566-573.
- 35Ben-Shlomo Y, Fallon U, Sterne J, Brookes S. Do medical students with A-level mathematics have a better understanding of the principles behind evidence-based medicine? Med Teach. 2004; 26(8): 731-733.
