Robust extensions of the MUSA method based on additional properties and preferences

Abstract

The MUSA method is a collective preference disaggregation approach following the main principles of ordinal regression analysis under constraints using linear programming techniques. The method has been developed in order to measure and analyse customer satisfaction and it is used for the assessment of a set of marginal satisfaction functions in such a way that the global satisfaction criterion becomes as consistent as possible with customer's judgments. The main objective of the method is to assess collective global and marginal value functions by aggregating individual judgments. This study evaluates different extensions of the MUSA method with the introduction of additional constraints in the basic linear programming formulation of the method. These constraints concern special properties for the assessed average indices and additional customer preferences about the importance of the criteria and they may be modelled as multiobjective linear programming problems. The main aim of the study is to show how the introduction of these additional constraints and information may improve the stability of the estimated results. An illustrative example is presented in order to show the applicability of this approach.