Converting an odds ratio to a range of plausible relative risks for better communication of research findings

Odds ratios are a necessary evil in medical research; although used as a measure of effect size from logistic regressions and case-control studies, they are poorly understood. This paper provides practical advice for authors and readers on converting odds ratios to relative risks

[1]  J. Leonardi-Bee,et al.  Systematic identification and treatment of smokers by hospital based cessation practitioners in a secondary care setting: cluster randomised controlled trial , 2013, BMJ.

[2]  Jonathan J. Deeks,et al.  Down with odds ratios! , 1996, Evidence Based Medicine.

[3]  M. Munafo,et al.  Interventions for smoking cessation in hospitalised patients. , 2007, The Cochrane database of systematic reviews.

[4]  R. Steele,et al.  Understanding the Relationship Between Risks and Odds Ratios , 2006, Clinical journal of sport medicine : official journal of the Canadian Academy of Sport Medicine.

[5]  J. Protheroe.  Communicating risk , 2003, BMJ : British Medical Journal.

[6]  Peter Cummings,et al.  The relative merits of risk ratios and odds ratios. , 2009, Archives of pediatrics & adolescent medicine.

[7]  G. Guyatt,et al.  Tips for Teachers of Evidence-Based Medicine: Understanding Odds Ratios and Their Relationship to Risk Ratios , 2008, Journal of General Internal Medicine.

[8]  D. A. Luke,et al.  An Odd Measure of Risk: Use and Misuse of the Odds Ratio , 2001, Obstetrics and gynecology.

[9]  J. Pearl,et al.  Confounding and Collapsibility in Causal Inference , 1999 .