Usually, in clinical practice the maneuver selected is the one that achieves a favorable outcome with a direct percentage of superiority of at least 10 %, or when the number needed to treat is approximately equal to 10. While this percentage difference is practical for estimating the magnitude of an association, we need to differentiate the impact measures (attributable risk, preventable fraction), measures of association (RR, OR, HR), and frequency measures (incidence and prevalence) applicable when the outcome is nominal. And we must identify ways to measure the strength of association and the magnitude of the association when the outcome variable is quantitative. It is not uncommon to interpret the measures of association as if they were impact measures. For example, for a RR of 0.68, it is common to assume a 32 % reduction of the outcome, but we must consider that this is a relative reduction, which comes from relations of 0.4/0.6, 0.04/0.06, or 0.00004/0.00006. However the direct reduction is 20 % (60 % - 40 %), 2 %, and 2 per 100,000, respectively. Therefore, to estimate the impact of a maneuver it is important to have the direct difference and/or NNT.