包絡分析法における入出力項目の構造分析手法の提案

抄録

Data Envelopment Analysis (DEA) is one of evaluation methods and enables analysts to evaluate efficiencies of Decision Making Units (DMUs) with multiple input and output items. While DMUs were evaluated only in terms of efficiency, analysts cannot evaluate how efficient combinations of input and output items are. In order to evaluate the efficiencies of the combinations, we propose a method on the basis of DEA for evaluating structure of efficiency about input and output items based on conventional hierarchical approach. The proposed method is composed of four steps. In Step 1, dividing dataset, we construct a hierarchical structure. In Step 2, efficiency values are calculated for each divided dataset. In Step 3, nodes are integrated and visualized in Step 4. From visualized figure, analysts can evaluate characteristics of DMU structurally and find subsequent efficient items and key items which improve efficiency if this item is added to other items. A numerical example with the dataset of 2010 Quality of Life Index (thirty five DMUs, one input and five output items) is used to illustrate the features of the proposed method.