DESIGN AND EVALUATION OF THE QUASIMEME INTER-LABORATORY PERFORMANCE STUDIES - A TEST-CASE FOR ROBUST STATISTICS

The QUASIMEME laboratory performance studies have been designed accord ing to the recent IUPAC/ISO protocol. An overview of the design is giv en and, in addition to the Z-score for ranking the bias of laboratorie s, a term called 'P score' is introduced as an aid to the assessment o f the precision of the laboratories. The data have been evaluated usin g robust statistics. Little information is available on practical appl ications of robust statistics for the evaluation of inter-laboratory s tudies, therefore, part of the data have been used to compare two diff erent algorithms for robust statistics and the conventional ISO 5725 p rocedure. The data obtained from these intercomparison studies are het erogeneous in nature, and it is concluded that robust statistics have distinct advantages in assessing the data, but should not be used with out a critical examination of the dataset.