NF EN ISO 4259-5, M07-033-5 (01/2024)

This document specifies a statistical methodology for evaluating the expected agreement between two test methods that claim to measure the same property of a material and for determining whether a simple linear bias correction can further improve the expected agreement. This document is applicable to analytical methods that measure quantitative properties of petroleum or related products resulting from a multi-sample, multi-laboratory study (MSMLS). These types of studies include interlaboratory testing (ILS) conforming to the requirements of ISO 4259-1, or equivalent, and proficiency testing programs (PTP) conforming to the requirements of ISO 4259-3, or equivalent, but not limited to it. The methodology specified in this document establishes the limit value of the difference between two results, when each result is obtained by a different operator using a different device and applying the two methods X and Y, respectively, on an identical material. One of the methods (X or Y) has been subject to appropriate bias correction to agree with the other method in accordance with this procedure. This limit is referred to as inter-method reproducibility. It is expected, with a probability of 5%, that this value will be exceeded under normal and correct conditions of application of these two methods due to random variation. NOTE Additional conditions for the application of this methodology are given in 5.1 and 5.2.
(Automatic translation from French)