Methodology for uncertainty characterization of performance measures

Purpose - The purpose of this paper is to present a methodology to represent the uncertainty generated in performance measures (PMs) during the operational step or "use step" of the performance measurement process (PMP). The different steps of the methodology are described and exemplified through an application example.Design/methodology/approach - An index that reflects the level of uncertainty originated by the factors and the strength of their inter-relationships is developed through the use of graph theory. A graph is developed considering all sources or factors of uncertainty that may be present in this process. Based on the graph, the methodology includes the use of a matrix and the determination of the associated permanent function which is used for determining the uncertainty index.Findings - During the development of the methodology, it was found that the use of a scale that includes zero for assigning values of the elements of the matrix is not appropriate when using graph theory and permanent function calculation, since in this case the permanent function is insensible to changes in some matrix elements.Originality/value - This paper identifies all the sources that can affect the quality of performance measurement values during the operational step of the PMP and proposes a method to characterize the strength of this uncertainty. Beyond alerting decision makers to the level of uncertainty associated with a PM, it also allows defining appropriate actions to improve PMs' quality.This work has been supported by FCT - Fundação para a Ciência e Tecnologia within the Project Scope: PEst-OE/EEI/UI0319/2014.