The first question that we can ask when looking at the results of a clinical trial, is whether the results might just be due to the play of chance (with no true difference between the treatment and control). If the likelihood is less than 5% that this could be a chance finding (P<0.05), then the results are regarded as statistically significant. But is the benefit (or harm) from the treatment big enough to be clinically important.

We cannot tell how much difference a treatment makes from the P value! We need to compare the size of the treatment effect with a measure that has been shown to be big enough to make a difference to patients. This is known as the Minimum Important Difference (MID).

It may be tempting to concluded that a treatment that makes an average difference of less than the MID may not be clinically worthwhile. However this is not necessarily so, and if you want to find out more please have a look at the paper by Charlotta Karner and myself published in the BMJ in November 2015.

Cates C, Karner C. Clinical importance cannot be ruled out using mean difference alone. BMJ (Clinical research ed 2015;351(nov20 4):h5496-h96 doi: 10.1136/bmj.h5496