A METHOD FOR DECISION MAKING BASED ON PROBABILISTIC INFORMATION AND DISTANCE MEASURES
University of Barcelona (SPAIN)
About this paper:
Appears in: EDULEARN10 Proceedings
Publication year: 2010
Conference name: 2nd International Conference on Education and New Learning Technologies
Dates: 5-7 July, 2010
Location: Barcelona, Spain
Abstract:We develop a new approach for decision making based on the use of distance measures and we apply it in research management. We use the probabilistic ordered weighted averaging weighted averaging (POWAWA) operator. Thus, we are able to consider the subjective and the objective probability and the attitudinal character of the decision maker in the same formulation. For doing so we introduce a new aggregation operator: the POWAWA distance (POWAWAD) operator. It is a new aggregation operator that uses distance measures in a unified framework between the probability, the weighted average and the OWA operator that considers the degree of importance that each concept has in the aggregation. Note that the POWAWA operator is included as a particular case when one of the sets of the POWAWAD operator is empty. Moreover, the POWAWAD operator includes a wide range of aggregation operators including some new relevant ones of special interest. For example, we could mention the maximum distance, the minimum distance, the maximum probabilistic weighted averaging distance (Max-PWAD), the minimum probabilistic weighted averaging distance (Min-PWAD), the probabilistic OWA distance (POWAD), the OWAWA distance (OWAWAD), the PWAD, the probabilistic distance (PD), the WA distance (WAD), the OWAD, the arithmetic POWAD, the double arithmetic OWAD, the arithmetic PWAD, the double arithmetic PD, the arithmetic OWAWAD and the double arithmetic WAD. We also develop an application of the new model in a decision making problem in research management. We analyze the general strategy or policy that a government should make the next period concerning the investment in research and development (R&D). We see that this model is very broad because it is able to consider many different scenarios depending on the type of information that we want to use in the problem.
Keywords: Decision making, research management, probability, distance measure, aggregation operators.