Measurement Uncertainty and Information Enabled Decision Making

It is widely accepted that in many industrial and commercial applications, as well as in the areas of health, safety, environmental protection, and forensics, decisions are mostly based on measurement results that are compared with one or more threshold values to state whether the measured quantity conforms to tolerance limits, or maximum admissible limits set by Standards or Laws. It is also known that the risk of making the wrong decision always exists, and is closely related to the credibility of the data entered in the decision-making process. When the input data are measurement results, their credibility is evaluated in terms of measurement uncertainty. Different decision rules have been proposed in literature and in the Standards, the ISO Std. 14253-1 and ISO Guide 98-4 above all, which consider measurement uncertainty, evaluated according to the recommendations of the Guide to the expression of Uncertainty in Measurement (GUM), in conformity assessment. However, given the tolerance limit, they do not fully explore the relationship between the measured value, measurement uncertainty, and the risk of wrong decision, and how any of them can be set, given the two other ones. This paper aims to discuss how to establish suitable decision rules, fully explain the underlying assumptions about measurement uncertainty and risk, and show how the proper definition of the decision rule may increase efficiency by reducing costs and may, consequently, represent a step forward in the direction of sustainability.