具有非期望产出的随机DEA模型研究  

Research on Stochastic DEA Model for Undesirable Outputs Evaluation

作　　者：朱佳欣 孙玉华[1] 杨丽明[2] 

机构地区：[1]北京科技大学数理学院,北京海淀100083 [2]中国农业大学理学院,北京海淀100083

出　　处：《经济数学》2015年第3期73-77,共5页Journal of Quantitative Economics

基　　金：国家自然科学基金项目(11471010)

摘　　要：为解决含有不确定信息的非期望产出效率评价问题,建立了一个非期望产出的随机DEA模型.该模型将非期望产出作为负期望产出进行处理,引入了期望效率值、显著性水平来刻画随机问题,并通过机会约束规划的相关知识将模型转化为确定形式.对模型的最优值的相关性质进行了探讨,说明最优值与期望效率值、显著性水平之间的关系.最后给出数值实验说明该模型的有效性.In order to solve the evaluation problem with undesirable outputs and uncertain information,this paper es-tablished a stochastic DEA model with undesirable outputs.The model treats undesirable outputs as negative desirable outputs. Meanwhile,it introduces the desired value and the efficiency of the significant level to describe the stochastic problem.By using the knowledge of chance constrained programming,we derived a deterministic equivalent model,discussed the related proper-ties of the optimal value of the model,and explained the relationship among the optimal value,the efficiency value and the sig-nificant level.Finally,numerical experiments were presented to illustrate the validity of the model.

关 键 词：数据包络分析 非期望产出 随机性 

分 类 号：O221.2[理学—运筹学与控制论]