Skip to Main Content
Different approaches than those framed strictly within the theory of probability and recommended by the GUM have been proposed during the last recent years for uncertainty expression and estimation. The one based on Random-Fuzzy Variables (RFV) appears to be the most promising one, since it is based on the theory of evidence, that encompasses both the probability and possibility theories as particular cases. The correctness of the final uncertainty estimation depends, quite directly, on the way the RFVs are built, which depends on the available metrological information. After briefly recalling the fundamentals of the RFV approach, this paper discusses how the available information should be exploited to attain correct results.