• The authors present the basic assumptions used in linear regression analysis and a simple methodology for checking if they are satisfied before use in research.

    They say that while linear regression is a powerful statistical model when used correctly, because the model is an approximation of the long-term sequence of any event, it requires assumptions to be made about the data it represents in order to remain appropriate.

    Their impression is that many clinical researchers have misconceptions about the assumptions of linear regression, particularly the so-called ‘normality assumption.’ They say this confusion is perhaps partly generated by the inconsistent description from various texts and online resources about the assumptions underlying linear regression.

    Their article discusses the mathematical foundations of linear regression and its assumptions with a target audience of clinical researchers in mind. They propose a simple methodology to check that these assumptions are fulfilled before linear regression is applied and that this fulfilment is routinely reported in the discussion of statistical methods in clinical research.