Statistics calculators

There are numerous statistical calculators available. These should be used as a guide only. Medical and other decisions should NOT be based on the results of these calculators. Although they have been tested, we cannot guarantee the accuracy of their calculations or results.

The following statistical calculators will be of particular interest:

• Odds Ratio and Relative Risk
• Benefit Increase / Number Needed to Treat Multicalc
• Risk Reduction / Number Needed to Treat Multicalc
• Bayesian Statistics I MultiCalc
• Bayesian Statistics II MultiCalc
• Likelihood Ratio MultiCalc
• Negative Predictive Value of a Test
• Positive Predictive Value of a Test

The first calculator can be used to assess relative risk (RR) and whether a treatment has a statistically significant effect. To do this, you need:

• The total number of people randomized to the experimental (treated) group and the total number (AR) of events in the experimental group (ART), plus
• The total number of people randomized to the control group and the total number (AR) of events in the control group (ARC).

See how to calculate risk for further information.

Formulae of risk terms
AR (absolute risk) = the number of events (good or bad) in treated or control groups, divided by the number of people in that group
ART = the AR of events in the treatment group
ARC = the AR of events in the control group
RR (relative risk) = ART / ARC
RRR (relative risk reduction) or RRI (relative risk increase) = (ARC-ART) / ARC or 1 - RR
ARR (absolute risk reduction) or ARI (absolute risk increase) = ARC - ART
NNT (number needed to treat) or NNH (number needed to harm) = 1 / ARR

For the detailed definition of the risk terms used, please see a glossary of EBM terms.

Content created by BMJ Knowledge Centre