Another possible reason is that confidence intervals are often embarrassingly wide. It’s hardly reassuring to report that the average improvement was 12 ± 9, or even 12 ± 15.

Peter Hall, Theoretical Comparison of Bootstrap Confidence Intervals, The Annals of Statistics, Vol. 16, No. 3 (Sep., 1988), pp. 927-953 Free online reading for over 10 million articles Save and ...

Hunyong Cho, Gregory J. Matthews, Ofer Harel, Confidence Intervals for the Area Under the Receiver Operating Characteristic Curve in the Presence of Ignorable Missing Data, International Statistical ...