基于C^2W模型的广义数据包络分析方法  

Generalized data envelopment analysis method based on C^2W model

作　　者：马生昀[1,2] 马占新[1,3] 

机构地区：[1]内蒙古大学数学科学学院,呼和浩特010021 [2]内蒙古农业大学理学院,呼和浩特010018 [3]内蒙古大学经济管理学院,呼和浩特010021

出　　处：《系统工程理论与实践》2014年第4期899-909,共11页Systems Engineering-Theory & Practice

基　　金：国家自然科学基金(71261017;70961005);内蒙古自治区自然科学基金重点项目(2010zd34)

摘　　要：传统数据包络分析(data envelopment,analysis,DEA)方法的参照系为决策单元全体,而许多实际问题的参照系可能会有多种形式,因此用传统DEA方法评价该类问题时遇到困难,广义DEA方法在评价该类问题时则存在一定的优势.为了进一步完善广义DEA方法的理论体系,给出基于C^2W模型的输出型广义DEA模型.讨论基于C^2W模型的输入型和输出型广义DEA模型中决策单元的Sam-DEAd有效性的判别条件,广义DEA模型与传统DEA模型之间的关系,SamDEAd有效性与相应的多目标规划的Pareto有效之间的关系,决策单元的投影性质,利用样本前沿面的d移动对决策单元进行有效性排序.The reference system of the traditional data envelopment analysis （DEA） method is all the decision making units （DMUs）, but reference systems of many practical problems have many forms, so using traditional DEA method to evaluate this kind of problems encounters difficulties, but generalized DEA method has certain advantages. For further perfecting the theory of generalized DEA method, the output- oriented generalized DEA model based on C2W model is given. The conditions of Sam-DEAd efficiency, the relationship between generalized DEA method and traditional DEA method, the relationship between Sam-DEAd efficiency and Pareto efficiency of corresponding multiple objective programming, property of projection of DMU and ranking method of DMU by the d-moving of the sample production frontier were disscussed.

关 键 词：广义数据包络分析 输入型 输出型 C2W模型 决策单元 样本单元 DEA有效 Pareto有效 

分 类 号：N94[自然科学总论—系统科学]