统计研究

• 论文 • 上一篇    下一篇

我国科技创新体系产出机制的门槛效应研究

谢兰云 王维国   

  • 出版日期:2016-02-15 发布日期:2016-03-02

Study on the Threshold Effect of Technology Innovation Output Mechanism in China

Xie Lanyun & Wang Weiguo   

  • Online:2016-02-15 Published:2016-03-02

摘要: 实现科技创新目标,采取有针对性科技发展政策的前提是对我国科技创新体系的特点有充分的认识。本文基于门槛回归模型,以R&D强度和R&D经费中企业经费所占比例作为门槛变量,对我国1985-2013年科技创新投入产出之间的关系进行了研究,结果显示在样本期内我国科技创新体系产出机制发生了转变,它们之间存在着两个门槛,R&D强度的门槛值分别为0.661%和1.325%,R&D经费中企业经费所占比例的门槛值分别为29%和67%。两个门槛变量回归的结果是一致的,即在不考虑经济发展水平这个控制变量的前提下,我国专利产出的增长都经历了从以R&D人员增长为主要影响因素到以R&D资本增长为主要影响因素的转变过程。在这个机制转变的过程中,我国科技体制改革和科教兴国战略发挥了重要作用。在此基础上,本文建立非线性模型描述它们之间的关系,结果与门槛回归模型的结果一致。

关键词: 科技创新, 非线性, 门槛回归, R&D

Abstract: Based on the threshold regression model, applying the R&D intensity and the proportion of enterprise investment in R&D spending as threshold variables, this paper researches the relationship between input and output of technology innovation during 1985-2013. The results show that the relationship had changed, and there is a R&D intensity threshold effect at 0.661% and 1.325%, the other at 29% and 67%. The regression results of two threshold variables are consistent, that is, the main influencing factor of patent output growth in China changes from R&D labour growth to R&D capital growth without considering the economic development level. In the process of mechanism transformation, the reform of science and technology system and the strategy of revitalizing China through science and education have played an important role. In addition, this paper builds nonlinear regression model to describe their relationship, and the result is consistent with the result of threshold regression model.

Key words: Technology Innovation, Nonlinear, Threshold Regression, R&D