Relative Risk Calculator
Calculate relative risk from a 2x2 exposure table with confidence interval bounds and interpretation.
What Relative Risk Means
Relative risk, also called the risk ratio, compares the probability of an event in an exposed group with the probability of the same event in a control group. It is widely used in epidemiology, clinical studies, and public-health reporting. Related tools: Post-Test Probability Calculator and P Hat Calculator.
Relative Risk Formula
From a 2×2 table, $a$ is exposed with the event, $b$ is exposed without the event, $c$ is control with the event, and $d$ is control without the event:
$$RR = \frac{a/(a+b)}{c/(c+d)}$$
$RR = 1$ means no difference. $RR > 1$ means higher risk in the exposed group. $RR < 1$ means lower risk in the exposed group.
Confidence Interval
The log method interval is
$$\exp\left(\ln(RR) \pm z \sqrt{\frac{1}{a}+\frac{1}{c}-\frac{1}{a+b}-\frac{1}{c+d}}\right)$$
If the interval includes 1, the observed difference is not statistically significant at that confidence level. Larger samples shrink the interval. For sample planning, see the Sample Size Calculator.
Example
If 24 of 200 exposed people have the event and 9 of 200 controls have it, then $RR = 0.12 / 0.045 = 2.67$. The exposed group has about 2.67 times the event risk of the control group.
Frequently Asked Questions
Is relative risk the same as odds ratio?
No. Relative risk compares probabilities. Odds ratio compares odds. They are close when the event is rare, but they diverge when the event is common.
What if the control group has zero events?
Relative risk is undefined because the control risk is zero. You need at least one control event, or a different estimator that adds a continuity correction.
Does RR less than 1 mean the exposure is protective?
It means the event was less common in the exposed group. That can suggest a protective association, but study design, confounding, and the confidence interval still matter.
Why does a small study have a wide confidence interval?
The standard error of ln(RR) grows when cell counts are small. A wide interval means the data are compatible with a large range of true risk ratios.
Can I use percentages instead of counts?
The formula needs counts, or risks that come from counts. Enter the number of people in each cell, not percentages.