Fayers and Hays (2013, May 31).

Fayers, P. M., & Hays, R. D.  (2013, May 31 published online first).  Don't middle your MIDs: Regression to the mean shrinks estimates of minimally important differences.  Quality of Life Research.

Abstract

Minimal important differences (MIDs) for patient-reported outcomes (PROs) are often estimated by selecting a clinical variable to serve as an anchor.  Then, differences in the clinical anchor regarded as clinically meaningful or important can be used to estimate the corresponding value of the PRO.  Although these MID values are sometimes estimated by regression techniques, we show this this is a biased procedure and should not be used; alternative methods are proposed.
http://link.springer.com/article/10.1007%2Fs11136-013-0443-4