Evaluation for a stability of fuzzy decision making using a sensitivity analysis

The Analytic Hierarchy Process (AHP) was proposed by Saaty (1977) and has been widely used in decision making, since it incorporates the natural feelings of human beings. On the other hand, fuzzy AHP, which is an extension of normal AHP, is one method of fuzzy decision making. We can obtain two types of decisions by using fuzzy measurement. When we actually use AHP, it often occurs that the best alternative cannot be found, since there is not a great deal of difference in the overall weights of the alternatives. Thus, it is very important to investigate how the components of a pairwise comparison matrix exert influence on the weights. Up to now two methods have been proposed as sensitivity analysis of the weights of the normal AHP. However, they have defects. Further, sensitivity analysis has not been proposed for fuzzy AHP. Accordingly, we propose new sensitivity analyses of the weights of normal AHP and fuzzy AHP. They can be easily used without changing the structure of the data.