两阶段DEA前沿面投影问题研究——兼对我国上市银行运营绩效进行评价

发布时间：2018-06-18 15:04

本文选题：两阶段DEA + 有效前沿面　；参考：《中国管理科学》2012年02期

【摘要】：DEA方法,即数据包络分析方法,是一种用于评价决策单元(Decision Making Units,DMUs)相对有效性的实证方法。近年来DEA方法已经广泛的应用于各行各业的绩效评价中,并发展出两阶段DEA方法。两阶段DEA方法相对于传统DEA方法的优势在于,它不但可以提供被评价对象的总体效率值,还可以分别生成每一阶段的效率值。但正是由于中间要素的存在,按照传统的DEA方法来调整两阶段DEA投入、产出要素的优化过程已不能成功投影在有效前沿面上。本文基于两阶段DEA方法,通过加入"虚拟中间要素"在两阶段DEA中嵌入一个"虚拟阶段",这样不但完善了两阶段DEA的逻辑结构,而且成功的将被评价单元投影到有效前沿面。最后本文应用以上方法对我国上市银行的运营绩效进行了实证分析。实证结果令我们意外的是,国有商业银行运营绩效优于股份制银行。
[Abstract]:DEA, or data Envelopment Analysis (DEA), is an empirical method used to evaluate the relative effectiveness of decision making Units (DMUs). In recent years, DEA method has been widely used in the performance evaluation of all walks of life, and a two-stage DEA method has been developed. The advantage of the two-stage DEA method over the traditional DEA method is that it can not only provide the total efficiency value of the evaluated object, but also generate the efficiency value of each stage separately. However, because of the existence of intermediate elements and the adjustment of two-stage DEA input according to the traditional DEA method, the optimization process of output elements can not be successfully projected on the effective frontier. Based on the two-stage DEA method, a "virtual stage" is embedded in the two-stage DEA by adding "virtual intermediate elements", which not only improves the logical structure of the two-stage DEA, but also successfully projects the evaluation unit to the effective frontier. Finally, this paper applies the above methods to the empirical analysis of the operational performance of listed banks in China. The empirical results surprise us that the operating performance of state-owned commercial banks is better than that of joint-stock banks.
【作者单位】：吉林大学商学院;
【基金】：教育部人文社会科学重点研究基地重大项目(2009JD790017) 国家自然科学基金青年项目(71001044)
【分类号】：F832.2;F224

【参考文献】