统计研究 ›› 2019, Vol. 36 ›› Issue (11): 113-124.doi: 10.19343/j.cnki.11-1302/c.2019.11.010

• • 上一篇    

动态面板空间随机前沿模型的参数估计及应用

任燕燕 吕洪渠 王娜   

  • 出版日期:2019-11-25 发布日期:2019-11-28

Dynamic Panel Spatial Stochastic Frontier Model

Ren Yanyan Lv Hongqu Wang Na   

  • Online:2019-11-25 Published:2019-11-28

摘要: 生产效率一般会受到空间相关性和时间滞后效应的影响,不易准确测算。本文考虑时空双重滞后特征,提出一种动态面板数据空间随机前沿模型,针对模型的内生性问题,借鉴已有的估计方法,本文提出一种广义矩估计方法(Generalized Method of Moments,GMM),并证明了参数估计的一致性。在应用分析中,利用本文所提出的理论模型实证分析了我国战略性新兴产业发展的效率,该理论模型能够客观、科学地测算技术效率,实证结论验证了理论模型的应用效果。

关键词: 面板数据, 空间计量模型, 随机前沿分析, GMM

Abstract: Production efficiency is often affected by spatial correlation and time lag effect and is not easy to measure accurately. Considering the spatial temporal dual lag, this paper proposes a dynamic panel data spatial stochastic frontier model. Due to the endogenous problem of the model, drawing on the experience of the existing estimation methods, we put forward a new method of Generalized Method of Moments (GMM) and prove the consistency of the estimator in statistics. An example is given to demonstrate the effectiveness of the estimation method in solving practical problems. In the application example, the theoretical method constructed in this paper is used to verify the existence of spatial temporal dual lag effect in the development of China’s strategic emerging industries. The application of the dynamic panel spatial stochastic frontier model is helpful to accurately calculate the technical efficiency, and the empirical results reflect the application value of the theoretical method.

Key words: Panel Data, Spatial Econometric Model, Stochastic Frontier Analysis, GMM