基于决策者偏好及赋权法一致性的组合赋权法

Combination weighting approach based on the decision-maker's preference and consistency of weighting methods

属性权重的确定是多属性决策中的一个关键而又难以解决的问题,针对现有主观赋权法和客观赋权法的不足,提出了一种新的组合赋权法。该方法同时考虑决策者对赋权方法的偏好及赋权方法的一致性程度,将这两个因素通过凸组合的方式反映在组合权重计算公式的加权系数中,其中反映决策者对某种赋权方法偏好度的加权系数可用AHP法来确定,反映一种赋权方法与其它赋权方法一致性程度的加权系数用Spearman等级相关系数来计算。给出了这种组合赋权法的具体步骤,并通过应用实例说明了该方法的合理性。

Determining the weights of attributes is crucial to multi-attribute decision-making, but it is very difficult. In view of the shortage of the present subjective and objective weighting methods, a new combination weighting approach is put forward. This approach considers the decision-maker's preference to the weighting methods and consistency degree of these weighting methods. Through convex combination, these two factors are put in the weighting coefficient of a formula which is used to calculate combination weight. The weighting coefficient which reflects the decision-maker's preference to the weighting method is determined by AHP, and the weighting coefficient which reflects consistency degree of a weighting method to the others is calculated by Spearman ranking correlation coefficient. Steps of this new combination weighting approach are given, and a numerical example is used to illustrate its reasonability.