摘要
RAM-DEA模型具有非径向性、指标多样性等特点,但模型中一维权重参数未充分考虑决策单元与评价指标的相互影响,导致测得的效率可能存在偏差。在以往研究的基础上,考虑决策单元与多种投入、产出指标的差异,建立优化权重RAM-DEA模型,构建了以计算机数、网站数为信息化投入,能源、劳动力、资本为自然投入,工业增加值为期望产出,温室气体与总颗粒物排放量为非期望产出的评价指标体系,并对中国39个工业行业综合效率进行评价。通过比较模型改进前后测算的综合效率值,发现改进后模型测得的效率值能反映出工业行业间差异。
The RAM-DEA model has the characteristics of non-radiality and index diversity. However, the parameters designed in the model do not fully consider the interaction between decision making units（DMU） and various indices, which may cause bias. On the basis of previous research, considering the differences between input/ output indicators and decision making unit, we establish a weightoptimized RAM-DEA model.The number of computers and websites are included in information input, while energy, labor, capital are takenas natural inputs, industrial profit as expected output,greenhouse gas and total particulate emissions as undesirable output. The empirical study of China＇s 39 industrial sectors shows the comprehensive efficiency resulted from the previous model and weightoptimized RAM-DEA model. We can find that the weightoptimizing RAM-DEA model can reflect differences of various industrial sectors through accounting.
出处
《科技管理研究》
CSSCI
北大核心
2018年第1期57-65,共9页
Science and Technology Management Research
基金
国家自然科学基金面上项目"面向小样本多属性决策的软集合理论及其应用研究"(71171209)
"面向不确定性混频数据的软集合预测模型与方法研究"(71671019)
