Method agreement analysis: a review of correct methodology

Abstract

The correct approach to analyzing method agreement is discussed. Whether we are considering agreement between two measurements on the same samples (repeatability) or two individuals using identical methodology on identical samples (reproducibility) or comparing two methods, appropriate procedures are described, and worked examples are shown. The correct approaches for both categorical and numerical variables are explained. More complex analyses involving a comparison of more than two pairs of data are mentioned and guidance for these analyses given. Simple formulae for calculating the approximate sample size needed for agreement analysis are also given. Examples of good practice from the reproduction literature are cited, and common errors of methodology are indicated.