In this article, the authors used the sentence "...risk difference (i.e., treatment effect on the clinically important absolute scale)".
What did they mean by "clinically important absolute scale"?
Did they mean by "risk difference (RD) (i.e., treatment effect on the clinically important absolute scale)" = "the absolute risk reduction (ARR)"?
Or they meant: if there is a treatment effect, it should not only be statistically relevant but also clinically important?
Thank you for your help!
The language is a stretch.
If they cite no source, it is because they actually mean risk difference is clinically important and an absolute scale. Rather than clinically important, risk difference is conservative and less likely to be exaggerated by a clinical audience, compared with risk ratio or the nefarious odds ratio. This is especially true for rare events. If the probability of an event is 5% in group A and 3% in group B, the risk difference is 2%, not 66%.
Absolute risk reduction is a causal term, but yes measured on the same scale.
