Number needed to treat calculator
Enter events and totals for the treatment and control groups.
Event table
| Group | Event | No event | Total | Risk |
|---|---|---|---|---|
| Fill in the fields above — the result is computed on this page. | ||||
How to use this page
- Enter event counts and totals for both groups.
- Inspect the risk-difference sign.
- Read NNT for benefit or NNH for harm.
What this page does not do: The calculator gives point estimates without confidence intervals and does not adjust for group differences. Equal risks imply an infinite NNT and are returned as no finite result. This tool does not replace clinical judgment.
Further reading
NNT is the reciprocal of absolute risk reduction. It estimates how many participants need the intervention to prevent one additional event during the stated period.
When treatment risk is higher, the same calculation gives NNH: the number needed for one additional harmful event.
Frequently asked questions
Should NNT be rounded?
For practical decisions it is commonly rounded up for benefit; also report the unrounded estimate and confidence interval.
Why does follow-up time matter?
Risk and NNT depend on the period during which events were counted.
See also
ACF and PACF autocorrelation calculator
Calculate ACF and PACF across time-series lags. Review the chart, reference bounds and coefficient table.
Adjusted R-squared calculator
Convert R² to adjusted R² using the number of observations and predictors in a regression model.
Beta distribution calculator
Calculate beta density, CDF, upper tail and quantile together with its mean and variance.