I thank Keene et al for their letter.1 I am pleased to clarify the issues they have raised about my paper.2 First, I agree that when dealing with recurrent events such as exacerbations, it is statistically more informative to analyse all events with tools such as incidence rates and rate differences. The point of my paper, however, was that inverting these rate differences and calling the result a number needed to treat (NNT) is simply wrong. For example, while the rates of chronic obstructive pulmonary disease (COPD) exacerbation from the TORCH trial are valid representations of …