On the interpretation and analysis of a degree-of-equivalence

The degree-of-equivalence between the standards realized by two laboratories comprises the difference between these standards and the uncertainty in this difference. However, the exact way in which these two pieces of information are to be used has not been prescribed. This paper shows how the degree-of-equivalence can be used for three different purposes: (i) to assess the mutual compatibility of the standards with a view to identifying problems in one or other measurement procedure; (ii) to decide if the standards are interchangeable without modification for a specific application; and (iii) to obtain a suitable adjustment term and its uncertainty when one standard is to be used with modification in place of another. In particular, the degree-of-equivalence is used with an explicit statistical model to define a `degree-of-compatibility' for the first purpose and a `degree-of-interchangeability' for the second purpose. The analysis is also applicable for the degree-of-equivalence between a participating laboratory and a comparison reference value.