Absolute and Relative Risk Reduction Calculator
Treatment Effect Calculator
Enter event rates as proportions to estimate absolute and relative effects. Example: 20% = 0.20.
Understanding the results
Absolute risk reduction (ARR) is the control event rate minus the experimental event rate (CER − EER). When this difference is positive for an undesirable event, the intervention group has fewer events. When it is negative, the event rate is higher in the experimental group; this is an absolute risk increase (ARI).
Relative risk reduction (RRR) is (CER − EER) / CER. It expresses the absolute difference relative to the control event rate. RRR is undefined when CER is zero, and it can be negative when the experimental event rate exceeds the control rate.
Number needed to treat (NNT) is the reciprocal of a positive ARR. For an increased risk of an undesirable event, the reciprocal of the absolute risk increase is presented as number needed to harm (NNH). Conventionally, these values are rounded up to the next whole number.
Clinical context and limitations
- Interpret ARR, RRR, and NNT/NNH together; relative effects alone can obscure the absolute magnitude of benefit or harm.
- State the outcome definition, comparator, population, and follow-up duration when reporting these measures. NNT/NNH depends on baseline risk and the time horizon.
- This calculator uses simple event proportions. It does not calculate confidence intervals, account for censoring in time-to-event data, or adjust for differences between studies.
References
Guidance on absolute and relative risk differences and calculation and interpretation of NNT.
Official Cochrane Handbook chapterDefinition of NNT, reciprocal of ARR, and convention of rounding up to a whole number.
Official CEBM resourceDOI: 10.1136/bmj.310.6977.452 · PMID: 7873954.
Publisher DOI pageClinical notes
Document key findings and keep a structured record for your own reference.
My notes
Review, edit, or remove notes saved in this browser.
Report an issue
Your feedback helps us improve the reliability and usability of this clinical tool.