存在保证域的模糊非径向偏好DEA模型--基于中科院24个研究所的实证分析

Fuzzy Non-radial DEA/PS Model with Assurance Regions——an Empirical Analysis based on 24 Institutes of CAS

数据包络分析(DEA)是一种非参数化的方法,用于评价具有类似输入和输出的决策单元的效率。传统的非径向DEA模型假设输入和输出数据均为准确值,且对权重变量不加以限制,本文构建了存在保证域的模糊非径向偏好DEA模型,并给出了一种基于模糊数截集的模型求解方法,有效地解决了输入和输出全部或部分为模糊数的决策单元评价问题。最后给出了一个中科院研究所效率评价的实例说明了方法的有效性。

Data Envelopment Analysis （DEA） is a non-parametric approach for performance assessment of a set of homogeneous Decision Making Units （DMUs）, which use similar inputs to produce similar outputs. Crisp data are commonly used in non-radial DEA models. However, inputs and outputs have been observed imprecise in many applications. At the same time, multipliers must be maintained at given levels for the production mechanism to work in reality. In this paper, a fuzzy non-radial DEA/PS model is proposed, which can deal with fuzzy data and decision maker＇s preference. The lower and upper bounds of fuzzy effi- ciency scores at different levels are determined based on a cuts. The proposed model and algorithm are used to evaluate the performance of 24 institutes of Chinese Academy of Sciences in the end.