Number needed to treat (NNT) and to harm (NNH)
Calculate the NNT or NNH from the event risks in the control and treated groups, with a confidence interval when you give the group sizes.
Your data does not go to our server. This tool runs in your browser; what you type or open never leaves your device.
This calculator needs JavaScript, because it calculates in your browser and sends nothing. Turn JavaScript on to use it. How it is calculated is explained below.
- NNT or NNH (rounded up in brackets)
- Absolute risk difference
- Relative risk reduction
- Confidence interval of the NNT
How it is calculated
The NNT is the reciprocal of the absolute risk difference; by convention it is rounded up to the next whole number. A negative difference is a number needed to harm.
The interval is found by inverting the interval of the risk difference.
ARR = CER − EER; NNT = 1 / ARRSE(ARR) = √[CER(1 − CER)/n₁ + EER(1 − EER)/n₂]; NNT interval = 1 / (ARR ± z × SE)
Worked example: Control risk 20 %, treated risk 10 %, 100 per group: NNT 10, interval 5.1 to 499.6.
Sources
These calculators support research; they do not replace the advice of a statistician or a clinician.
Questions
What does a confidence interval "to infinity" mean?
If the interval of the risk difference includes zero, the treatment may do no good or even harm, and the NNT interval runs through infinity. The tool then gives the two ends in the form recommended by Altman.