# Risk ratio

A risk ratio divides the probability of an outcome in an exposed group by the probability in an unexposed group. It is also called relative risk. If 20 of 100 sedentary people reach the outcome and 10 of 100 active people do, the risk ratio is 0.10 divided by 0.20, that is 0.50, a halving of risk. A value of 1.0 means no difference. The measure needs cumulative incidence, so it requires cohorts, randomised trials, or any design where the population at risk is known. Case-control studies cannot produce it directly, because sampling is done on the outcome. That gap is why odds ratios exist. The recurring failure is confusion with the odds ratio. Odds put non-events in the denominator, so the two measures diverge as the outcome becomes common. With risks of 20% and 10%, the odds ratio is 0.10/0.90 divided by 0.20/0.80, which equals 0.44, further from 1.0 than the risk ratio of 0.50. At a 40% baseline the gap widens sharply. Below roughly 10% baseline risk the two nearly coincide, which is the rare disease assumption. Relative measures also hide the absolute scale. A risk ratio of 2.0 on a baseline of 1 in 10,000 still describes a rare event, which matters for most supplement and screening claims.

## Sources

- Davies HTO, Crombie IK, Tavakoli M. (1998). When can odds ratios mislead?. BMJ. https://doi.org/10.1136/bmj.316.7136.989
- Zhang J, Yu KF. (1998). What's the relative risk? A method of correcting the odds ratio in cohort studies of common outcomes. JAMA. https://doi.org/10.1001/jama.280.19.1690
- Cummings P. (2009). The relative merits of risk ratios and odds ratios. Archives of Pediatrics & Adolescent Medicine. https://doi.org/10.1001/archpediatrics.2009.31

---

_Canonical: https://longevity-germany.com/en/glossary/risk-ratio · Part of Longevity Cities · Updated 2026-08-25_