Lecturer in Medical Statistics, University of Bristol, UK
Lecturer in Intensive Care Medicine, St George's Hospital Medical School, London, UK
An erratum to
In the original version of this article [1], the word 'binomial' was accidentally replaced with 'binary' in the fourth paragraph. The fourth paragraph should have read as follows:
'There are many other theoretical distributions that may be encountered in medical data, for example Binomial or Poisson [2], but the Normal distribution is the most common. It is additionally important because it has many useful properties and is central to many statistical techniques. In fact, it is not uncommon for other distributions to tend toward the Normal distribution as the sample size increases, meaning that it is often possible to use a Normal approximation. This is the case with both the Binomial and Poisson distributions.'