Novel approach to reducing uncertainty of drift estimate in international comparisons of relative humidity scales

International comparisons of relative humidity scales at the highest level are often challenging because of significant drift of the impedance-based transfer standard, which reduces the accuracy of comparison. Comparisons that are shorter or have fewer participants may be less affected by drift, but ultimately require more inter-linking with their inherent irreproducibility to compare all scales internationally. We addressed these issues in a large comparison of 21 laboratories from the European association of national metrology institutes (EURAMET), covering a range from 10%rh to 95%rh at air temperatures from 10 & DEG;C to 70 & DEG;C. In it, nine state-of-the-art transfer standards drifted on average between 0,6%rh and 1,8%rh, depending on the measurement point, while the participants can achieve calibration uncertainties on average between 0,2%rh and 1,5%rh. To produce useful comparison data even with significantly drifting transfer standards, we carefully planned the topology of the comparison and the number of transfer standards to be able to partly compensate for drift. This paper focuses on the approach we took in analysing the results to minimise the impact of instrument drift on the comparison outcome. We combined the estimated drift of the transfer standards together with the links drawn between the loops into so-called between-set variability. To calculate the reference value, we used an adjusted Paule-Mandel estimate where we modified the model equations to account for the three interlinked loops and solved for them using a non-linear least-squares fitting. This approach reduced the uncertainty in the drift estimates and the uncertainty in evaluated degrees of equivalence at most, but not all, of the measured values. We discuss the advantages of this approach to consider its applicability in future interlaboratory comparisons.