An examination of the effectiveness of multi-dimensional decision-making methods: A decision-making paradox

This paper presents the results of a study that compared four decision-making methods. The methods examined were the weighted sum model, the weighted product model, the analytic hierarchy process, and the revised analytic hierarchy process. Two evaluative criteria were used in an attempt to find the best method. The first criterion was to see if the method when accurate in a multi-dimensional situation remained accurate in a single-dimension case. The second criterion determined the stability of a method in yielding the same outcome when a nonoptimal alternative was replaced with a worse alternative. Tests were conducted using simulated decision problems where random numbers were used for the values of the many combinations of alternatives and criteria. The results illustrate the paradox of deciding on a single best decision-making method. While this paradox is not resolved, useful information is presented for comparing the four methods tested.