Max-min DEA模型及效率讨价还价均衡解  

Max-min DEA model and corresponding Nash bargaining solution

作　　者：吴德胜[1] 石琴[2] 汪明[1] 

机构地区：[1]中国科学技术大学商学院,合肥230026 [2]合肥工业大学机械汽车学院,合肥230069

出　　处：《管理科学学报》2005年第5期90-94,共5页Journal of Management Sciences in China

基　　金：国家自然科学基金资助项目(70371023);教育部博士点基金资助项目(20030358052);中科院2004出国项目资助项目;中科院研究生创新基金;中科大博士创新基金资助项目

摘　　要：建立一类新的DEA模型,即Max-min DEA模型.该模型通过最大化最小效率单元的效率,结合了自评与互评的思路,在一定程度上克服了仅仅采用自评思想的经典DEA模型的缺陷.文中Max-min均衡模型问题在于保护“弱小”单元的同时,有可能损害其它单元的效率.为克服该问题,文章通过Nash讨价还价模型求解Max-min均衡模型与CCR模型的讨价均衡解.最后用算例进行了演示计算.A new data envelopment analysis （max-min DEA） model is proposed by maximizing the efficiency of the minimal efficiency Units. The idea combing self-rated and other-rated schema is adopted in the proposed model. Thus, to some extent, two inter-related problems that are weak discriminating power and unrealistic weight distribution occurred in classical DEA are solved. In this model, efficiency criteria more restrictive than the classical one will yield fewer efficient DMUs and will allow less flexibility for input/output weight distribution. The DEA-Nash equilibrium methods may hurt the efficiency of other DMUs in order to “protect” the minimal efficiency DMU. To deal with the problem, Nash Bargaining approach is applied to yield a solution that characterizes the evaluation process. Finally, conclusions are demonstrated by an example.

关 键 词：数据包络分析 纳什均衡 规划 权重 讨价还价解 

分 类 号：O221[理学—运筹学与控制论] N94[理学—数学]