ll interventions differ, although some are more different than others

It is a well-known statement of statistical wisdom that all treatments differ. We could substitute the word ‘intervention’ or the phrase ‘surgical procedure’ for ‘treatment’ and qualify the word ‘differ’ by, for instance, saying “have different outcomes”. Yet, in doing so we challenge far more than semantics, questioning the relevance of much of the research reported in The Bone and Joint Journal, and the wider medical literature. For example, the DRAFFT study compared the clinical effectiveness of Kirschner wire fixation with locking plate fixation for patients with a dorsally displaced fracture of the distal radius. Selectively picking out the key result of the paper one would conclude that there was no difference in outcomes between the two groups; thus that there was no difference between the treatments. This result seems to contradict the first statement in this paragraph, which follows from the simple argument that by definition all treatments must be different because no two things can ever be exactly the same in every respect. This sounds like a matter of philosophical interest only, but understanding how we reconcile this apparent contradiction helps shed light on an issue that continues to be a cause of confusion for many authors submitting papers to our Journal.