VALIDATION OF ANALYTICAL METHODS USING A REGRESSION PROCEDURE

The evaluation and validation of analytical methods and instruments re quire comparison studies using sample material for testing accuracy an d precision. In analytical chemistry, the commonly accepted means of a nalyzing data from method comparison studies is least-squares regressi on analysis, a model which has limitations. In this paper, the results from ordinary least-squares and many other regression approaches reco mmended in the literature were compared with a new regression procedur e that takes into account the errors in both variables (methods). Afte r a discussion of the properties of the regression procedure, recommen dations are given for carrying out a method comparison study using inf ormational analysis of variance. The efficiency of the regression proc edure proposed is demonstrated by applying it to different data sets f rom published literature.