The phenomenon of regression to the mean and clinical investigation of blood cholesterol lowering drugs

Abstract

The phenomenon of regression to the mean is widespread. It may affect any quantitative biological data in which there is "within subject" variability. It is demonstrated, as an example in practice, by a shift from high to lower values with time in a selected subset of patients with an abnormally high blood cholesterol. The phenomenon will influence experiments involving before-after measurements of a continuous variable. An incorrect conclusion may be reached if investigators do not take regression to the mean into account when designing a clinical trial of hypolipidemic therapy. The reality of the phenomenon is illustrated by a prospective study.