边限检验理论及几点讨论  

Bounds Testing Theory and Some Discussions about It

作　　者：靳军会[1] 邱长溶[1] 

机构地区：[1]西安交通大学经济与金融学院,陕西西安710061

出　　处：《统计与信息论坛》2008年第7期14-19,28,共7页Journal of Statistics and Information

摘　　要：检验经济变量之间长期关系的协整技术要求变量是同阶单整的,这不可避免地涉及一定程度的预检验问题,而预检验问题会增加变量间长期关系分析的不确定性。当不能确定变量的单整类型时,边限检验理论提出了一个可以直接检验一个变量和一组解释变量之间长期关系的新方法。在介绍了边限检验方法中基本的VAR模型和假设及边限检验方法中用到的重要统计量——Wald统计量和T统计量及它们各自的渐近分布形式后,说明了边限检验理论在理论和实际运用当中需要注意的几个问题,最后通过实例分析说明了边限检验理论的运用。Co- integration techniques for testing the existence of relationship between variables in which the underlying variables are integrated of order one, this inevitably involves a certain degree of pre - testing, thus concerning a further degree of uncertainty into the analysis of level relationships. This paper introduces a new approach to the problem of testing the existence of a relationship between a dependent variable and a set of explanatory variables, when it is not known with certainty whether the underlying variables are trend- or first -difference stationary. After introducing the VAR model and hypothesis which underlying the PSS and the asymptotic distribution theory for the Wald and T- statistic, we provide some discussions about the bounds testing theory. In the end, through using the empirical study, we explain how to apply the bounds testing theory.

关 键 词：边限检验 长期关系 渐进分布 

分 类 号：F224.0[经济管理—国民经济]