The four indices for a binary outcome or therapeutic objective are: the odd
s ratio, the relative risk, the absolute benefit and the number of patients
to treat. For a continuous outcome, the effect size is the best choice. Th
e odds ratio approximates the relative risk. The difference may be large in
some instances. The number of patients to treat is the reciprocal of the a
bsolute benefit. Although they are built on the same two quantities, they a
re not interchangeable and should not be considered in the same way. Moreov
er, their meaning is not straight-forward and they can be misused.