带有非期望输出的广义随机DEA方法

GENERALIZED STOCHASTIC DEA METHOD WITH UNDESIRABLE OUTPUT

广义数据包络分析(DEA)方法是多输入多输出决策单元相对于任意同类样本单元进行相对效率评价的方法。当决策单元集作为样本单元集时,广义DEA方法即为相应的传统DEA方法。传统和广义随机DEA方法的研究还比较少。在实际生产过程中,有时输入输出指标可能存在随机性,同时在生产过程中可能产生污染物等负面输出,在DEA方法中称为非期望输出。针对以上2种可能出现的情况,本文讨论带有非期望输出的基本广义随机DEA方法,考虑样本单元和决策单元仅有非期望输出指标随机和所有输入输出指标均随机2种情况,分别利用期望值模型和机会约束规划进行确定性转化,给出相应的广义随机DEA有效的概念,从理论上初步解决了此类问题的有效性评价问题。

The generalized data envelopment analysis(DEA)method is a method for evaluating the relative efficiency of multiple input and multiple output decision-making units relative to the same kind of sample units.The generalized DEA method is the corresponding traditional DEA method when the decision-making unit set is taken as the sample unit set.The research on the traditional and generalized stochastic DEA method is still relatively few.In the actual production process,sometimes the input and output indicators may be random,and at the same time,the negative output such as pollutants may be generated in the production process,which is called undesired output in the DEA method.In view of the above two possible situations,the generalized stochastic DEA method with undesired output of"undesired output is random"and"all input and output are random"was studied in this paper.The deterministic transformation based on the expectation value model and chance constrained programming,and the corresponding concepts of the generalized stochastic DEA efficiency were given.The efficiency evaluation problem of this kind of problem was solved preliminarily in theory.