SMAA-2: Stochastic multicriteria acceptability analysis for group decisionmaking

Stochastic multicriteria acceptability analysis (SMAA) is a multicriteria d ecision support method for multiple decision makers in discrete problems. I n SMAA. the decision makers need not express their preferences explicitly o r implicitly. Instead. the method is based on exploring the weight space in order to describe the valuations that would make each alternative the pref erred one, inaccurate or uncertain criteria values are represented by proba bility distributions from which the method computes confidence factors desc ribing the reliability of the analysis. In this paper we introduce the SMAA -2 method, which extends the original SMAA by considering all ranks in the analysis. In situations where the "elitistic" SMAA may assess large accepta bility only for extreme alternatives without sufficient majority support, t he more holistic SMAA-2 analysis can be used to identify good compromise ca ndidates. The results are presented graphically. We consider also situation s where partial preference information is available. We demonstrate the new method using a real-life decision problem.