Modeling Attitude to Risk in Human Decision Processes: An Application of Fuzzy Measures
Fuzzy Sets and Systems
Several models of the human decision process have been proposed, classical examples of which are utility theory and prospect 11 theory. In recent times, the theory of fuzzy measures and integrals has emerged as an alternative meriting further investigation. Specifically, we are interested in the degrees of disjunction and conjunction and the veto and favor indices that represent the 13 tolerance measure of the decision maker. Though several theoretical expositions have appeared in contemporary literature, empirical studies applying these concepts to the realworld are scarce. In this paper,we adopt a model of strategic telecommunication investment 15 decisions from a research work involving a survey of executives. In our first study, we built fuzzy models corresponding to each individual decision maker and grouped the results based on the decision makers’ propensity to risk determined by their degrees of 17 disjunction.We then pooled the data sets from each group and analyzed the Shapley indices and the interaction effects. To contrast our approach to those of conventional nomothetic comparisons of decision policies, we grouped the decision makers based on a 19 clustering analysis of the individual linear regression models. For each cluster we pooled the data and analyzed the fuzzy measures learned from the data set. Our study not only serves as a demonstration of fuzzy measure analysis as a viable approach to studying 21 qualitative decision making but also provides useful methodological insights into applying fuzzy measures to strategic investment decisions under risk.