基于StoNED方法的三阶段DEA模型改进
|
摘要
由于受约束的极大似然估计法较难实现,目前国内关于StoNED方法实际应用的例子较少。为此,在三阶段DEA模型的第二阶段,尝试使用StoNED方法替代SFA方法,在给出管理无效率项和随机误差项标准差估计式的基础上,讨论不同随机前沿下分离管理无效率项的方法,以及环境变量的调整对混合误差项的影响。随后,通过分析基于StoNED方法改进的三阶段DEA模型的效率评价结果,对应用中存在的问题进行归纳总结,并进一步指出随后研究的方向。
The practical application of StoNED method is still rare in China because of the difficulty in realizing the constrained maximum likelihood estimation method. Therefore, in the second stage of three-stage DEA model, this paper tries to use the StoNED method to replace the SFA method. On the basis of the standard deviation estimation of management inefficiency terms and random error terms, the methods of separating management inefficiency terms under different stochastic fronts are discussed, and the influence of environmental variable adjustment on mixed error terms is discussed. Then, by analyzing the efficiency evaluation results of the improved three-stage DEA model by StoNED method, the problems in application are summarized and the subsequent research directions are further pointed out.
The practical application of StoNED method is still rare in China because of the difficulty in realizing the constrained maximum likelihood estimation method. Therefore, in the second stage of three-stage DEA model, this paper tries to use the StoNED method to replace the SFA method. On the basis of the standard deviation estimation of management inefficiency terms and random error terms, the methods of separating management inefficiency terms under different stochastic fronts are discussed, and the influence of environmental variable adjustment on mixed error terms is discussed. Then, by analyzing the efficiency evaluation results of the improved three-stage DEA model by StoNED method, the problems in application are summarized and the subsequent research directions are further pointed out.
引文
[1] Kuosmanen T.Stochastic nonparametric envelopment of data:Combining virtue of SFA and DEA in a unified framework[C].MTT Discussion Paper,2006.
[2] 籍艳丽,赵丽琴.一种效率测度的新方法:随机非参数数据包络分析法[J].统计与决策,2011(05):33-34.
[3] 林森.基于StoNED方法的中国商业银行绩效研究[J].统计与决策,2009(07):123-125.
[4] 周四军,王欣,胡瑞.中国商业银行X效率测度——StoNED方法与超效率DEA方法的比较研究[J].统计与信息论坛,2012,27(04):3-9.
[5] 陶永宏,邹嘉,苏昆.基于StoNED的中、韩、日造船业效率比较研究[J].江苏科技大学学报(社会科学版),2013,13(01):86-93.
[6] 袁丽静,杨琼.基于StoNED模型的技术效率半参数分析——以钢铁行业为例[J].财经问题研究,2015(05):35-41.
[7] 张华平.基于StoNED方法区域金融效率的测算[J].统计与决策,2016(14):145-148.
[8] 范德成,杜明月.高端装备制造业技术创新资源配置效率及影响因素研究——基于两阶段StoNED和Tobit模型的实证分析[J].中国管理科学,2018,26(01):13-24.
[9] Aigner D J,et al.Formulation and estimation of stochastic frontier production function models[J].Journal of Econometrics,1997(6):21-37.
[10] Jondrow J,et al.On the estimation of technical inefficiency in the stochastic frontier production model[J].Journal of Econometries,1982(19):233-238.
[11] Fried H O,et al.Accounting for environmental effects and statistical noise in data envelopment analysis[J].Journal of Productivity Analysis,2002,(17):157-174.
[12] 罗登跃.三阶段DEA模型管理无效率估计注记[J].统计研究,2012,29(04):104-107.
[13] 陈巍巍,张雷,马铁虎,刘秋繸.关于三阶段DEA模型的几点研究[J].系统工程,2014,32(09):144-149.
[14] Kuosmanen T,et al.What is the best practice for benchmark regulation of electricity distribution?Comparison of DEA,SFA and StoNED methods[J].Energy Policy,2013(61):740-750.
[2] 籍艳丽,赵丽琴.一种效率测度的新方法:随机非参数数据包络分析法[J].统计与决策,2011(05):33-34.
[3] 林森.基于StoNED方法的中国商业银行绩效研究[J].统计与决策,2009(07):123-125.
[4] 周四军,王欣,胡瑞.中国商业银行X效率测度——StoNED方法与超效率DEA方法的比较研究[J].统计与信息论坛,2012,27(04):3-9.
[5] 陶永宏,邹嘉,苏昆.基于StoNED的中、韩、日造船业效率比较研究[J].江苏科技大学学报(社会科学版),2013,13(01):86-93.
[6] 袁丽静,杨琼.基于StoNED模型的技术效率半参数分析——以钢铁行业为例[J].财经问题研究,2015(05):35-41.
[7] 张华平.基于StoNED方法区域金融效率的测算[J].统计与决策,2016(14):145-148.
[8] 范德成,杜明月.高端装备制造业技术创新资源配置效率及影响因素研究——基于两阶段StoNED和Tobit模型的实证分析[J].中国管理科学,2018,26(01):13-24.
[9] Aigner D J,et al.Formulation and estimation of stochastic frontier production function models[J].Journal of Econometrics,1997(6):21-37.
[10] Jondrow J,et al.On the estimation of technical inefficiency in the stochastic frontier production model[J].Journal of Econometries,1982(19):233-238.
[11] Fried H O,et al.Accounting for environmental effects and statistical noise in data envelopment analysis[J].Journal of Productivity Analysis,2002,(17):157-174.
[12] 罗登跃.三阶段DEA模型管理无效率估计注记[J].统计研究,2012,29(04):104-107.
[13] 陈巍巍,张雷,马铁虎,刘秋繸.关于三阶段DEA模型的几点研究[J].系统工程,2014,32(09):144-149.
[14] Kuosmanen T,et al.What is the best practice for benchmark regulation of electricity distribution?Comparison of DEA,SFA and StoNED methods[J].Energy Policy,2013(61):740-750.