A metrologist viewpoint on some statistical issues concerning the comparison of non-repeated measurement data, namely MRA Key Comparisons

Since the Mutual Recognition Arrangement (MRA) came into effect, many discussions are taking place about the Key Comparison (KC) protocols and the subsequent statistical treatment, concerning the experimental data to be collected and be analysed. The discussion presently going on is often omitting, or giving for granted, some preliminary important steps that, on the contrary, are still contentious. The paper is an attempt to list in a comprehensive way the above problems and to suggest ways to progress toward solutions.