What should we use when interpreting the results of a clinical trial -- are the differences between the drug and the placebo big, small or negligible? Is it meaningful for the patients? People have been using the MCID (minimal clinical importance difference) for this purpose for years but this practice is logically wrong. We advocate the use of the SWD (smallest worthwhile difference). Here is a video explaining this difference by Prof Salanti of the University of Bern. https://www.youtube.com/watch?v=1VgNnGWqhcI

The SWD should inform the calculation of the sample size for the next trial. But it is not exactly the d for the sample size calculation. Please see: https://www.youtube.com/watch?v=1VgNnGWqhcI