带有随机样本单元的广义数据包络分析方法  

Generalized DEA Method with Random Sample Units

作　　者：马生昀[1] 漆影帆 马占新[3] 龙梅[1] 吉日木吐[4] MA Sheng-yun;QI Ying-fan;MA Zhan-xin;LONG Mei;Jirimutu(School of Science,Inner Mongolia Agricultural University,Hohhot 010018,China;School of Mathematics and Statistics,Lanzhou University,Lanzhou 730000,China;School of Economics and Management,Inner Mongolia University,Hohhot 010021,China;Vocational and Technical College,Inner Mongolia Agricultural University,Baotou 014109,China)

机构地区：[1]内蒙古农业大学理学院,内蒙古呼和浩特010018 [2]兰州大学数学与统计学院,甘肃兰州730000 [3]内蒙古大学经济管理学院,内蒙古呼和浩特010021 [4]内蒙古农业大学职业技术学院,内蒙古包头014109

出　　处：《数学的实践与认识》2018年第24期223-231,共9页Mathematics in Practice and Theory

基　　金：国家自然科学基金(71661027,71661025);内蒙古农业大学基础学科科研启动基金项目(JC2014008)

摘　　要：广义数据包络分析(Generalized data envelopment analysis)方法是一种相对效率评价方法,能够获得决策单元相对于样本单元的比较信息.研究了基于随机样本单元对确定性决策单元进行评价的广义DEA模型,利用期望值和机会约束,将其转化为确定性规划.给出了决策单元GEDEA有效和GCDEA有效的概念及其判别,与多目标规划Pareto有效关系,以及利用移动因子进行有效性排序.Generalized data envelopment analysis method is a relative efficiency evaluation method,which can obtain the comparison information of the decision making units relative to sample units.In this paper,generalized DEA model which evaluate the deterministic decision making units based on random sample units is studied by transforming it to deterministic programming used expected value and chance constrained.The conception and discrimination of GEDEA efficiency and GCDEA efficiency of decision making units,the relationship with Pareto efficiency of the multi-objective programming,and sorting method of efficiency by the moving factor are given.

关 键 词：决策单元 样本单元 随机变量 期望值模型 机会约束规划 广义DEA有效 

分 类 号：O221.1[理学—运筹学与控制论]