The role of the minimum clinically important difference and its impact on designing a trial
Article first published online: 8 OCT 2010
Copyright © 2010 John Wiley & Sons, Ltd.
Volume 10, Issue 3, pages 250–256, May/June 2011
How to Cite
Chuang-Stein, C., Kirby, S., Hirsch, I. and Atkinson, G. (2011), The role of the minimum clinically important difference and its impact on designing a trial. Pharmaceut. Statist., 10: 250–256. doi: 10.1002/pst.459
- Issue published online: 16 MAY 2011
- Article first published online: 8 OCT 2010
- minimum clinically important difference;
- observed treatment effect
The minimum clinically important difference (MCID) between treatments is recognized as a key concept in the design and interpretation of results from a clinical trial. Yet even assuming such a difference can be derived, it is not necessarily clear how it should be used. In this paper, we consider three possible roles for the MCID. They are: (1) using the MCID to determine the required sample size so that the trial has a pre-specified statistical power to conclude a significant treatment effect when the treatment effect is equal to the MCID; (2) requiring with high probability, the observed treatment effect in a trial, in addition to being statistically significant, to be at least as large as the MCID; (3) demonstrating via hypothesis testing that the effect of the new treatment is at least as large as the MCID. We will examine the implications of the three different possible roles of the MCID on sample size, expectations of a new treatment, and the chance for a successful trial. We also give our opinion on how the MCID should generally be used in the design and interpretation of results from a clinical trial. Copyright © 2010 John Wiley & Sons, Ltd.