TimelyScholarFree Tools › Relative Risk Calculator
Calculate the relative risk with its confidence interval, plus the absolute risk difference and number needed to treat, from a 2×2 table.
FreeNo account neededYour data stays in your browser
| Event | No event | |
|---|---|---|
| Exposed / treatment | ||
| Unexposed / control |
| Relative risk (risk ratio) | 0.500 |
|---|---|
| 95% CI | 0.287 to 0.870 |
| p-value (two-sided) | 0.014 |
| Risk in first group | 15.0% |
| Risk in second group | 30.0% |
| Risk difference | -15.0% (95% CI -26.4% to -3.6%) |
| Number needed to treat (benefit) | 6.7 |
The risk in the first group is 0.50 times the risk in the second group (95% CI 0.29 to 0.87).
Events and non-events in each group.
90%, 95% or 99%.
Relative risk, risk difference and NNT.
Relative risk, or risk ratio, is the risk of an event in one group divided by the risk in another. A relative risk of 0.75 means the risk is 25% lower in the first group.
Relative effects should be read alongside absolute effects. The risk difference and number needed to treat show how many people are actually affected.
Relative risk is a ratio of risks; risk difference is their subtraction. A small relative change can mean a large absolute change when the baseline risk is high, and vice versa.
Relative risk is usually easier to interpret for cohort studies and trials. Odds ratios are used for case-control studies and logistic regression.