基于StoNED方法的三阶段DEA模型改进

Improvement of Three-stage DEA Model Based on StoNED Method

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.