Affiliation: | (1) European Commission, Joint Research Centre, Institute for Reference Materials and Measurements (IRMM), 2440 Geel, Belgium;(2) Nederlands Meetinstituut (NMi), Schoemakerstraat 97, 2600 AR Delft, The Netherlands;(3) European Commission, Joint Research Centre, Institute for Environment and Sustainability, Via Enrico Fermi-TP 730, 21020 Ispra, Italy |
Abstract: | The first part of this paper discusses some critical factors in planning and evaluation of isochronous stability studies. Recommendations on the number of time-points, number of items, and number of replicates to be measured on each unit are given. In general, more than two time-points should be used. The effect of batch heterogeneity can be eliminated by spreading the results over more units. An approach for combining two or more isochronous stability studies is developed in the second part. This approach includes a potential correction of the earlier stability study, pooling of data of the stability studies, and an uncertainty evaluation taking into consideration the uncertainty of the initial correction. The statistical basis for this approach is developed and equations for evaluation of the uncertainty of stability of the combined study are given. |