DETECTION OF BIAS IN METHOD COMPARISON BY REGRESSION-ANALYSIS

Regression analysis is often applied to validate a newly developed met hod against a reference method. The present work investigates The risk of not detecting a systematic difference between two analytical metho ds (=beta-error) and determines the number of points needed to detect a bias with a specified beta-error. Approximate formulae are proposed to predict the sample size required to detect from a regression analys is a proportional or a constant bias, i.e. a bias in the slope or in t he intercept. These results are compared with those of computer simula tions. Three different designs to distribute the data are studied, nam ely, a normal and a rectangular distribution over the whole measuremen t range as well as an experimental design where the measurements are p erformed at three fixed concentration levels. For a known straight lin e relationship, it is demonstrated that this last design is to be pref erred. A procedure is also proposed to simultaneously test slope and i ntercept of the orthogonal least-squares line. It is shown that, for a given number of data, an evaluation based on such a joint test allows a more reliable bias detection.