基于Bootstrap的变结构面板协整检验方法  

The Panel Cointegration Test with Structural Changes Based on the Bootstrap

作　　者：杨宝臣[1] 李晶晶[1] 

机构地区：[1]天津大学管理与经济学部

出　　处：《数量经济技术经济研究》2012年第9期151-160,F0003,共11页Journal of Quantitative & Technological Economics

基　　金：国家自然科学基金(71171144);教育部新世纪优秀人才支持计划(NCET-08-0397);教育部长江学者和创新团队发展计划(IRT1028);天津大学自主创新基金项目的资助

摘　　要：通过蒙特卡罗模拟试验证明小样本情况下结构变化的存在会影响Panel-ρ、Group-ρ检验方法的有效性,且影响大小与结构变化的类型相关。提出了一种将连续路径分块自举法与Panel-ρ、Group-ρ检验方法相结合的自举协整检验法,并分析了该方法在各种变结构协整模型下的检验有效性。结果表明,该方法的应用能够降低结构变化对协整检验功效的影响。最后运用所提出的自举协整检验方法对中国沿海地区的GDP与外商直接投资的协整关系进行了检验。This paper investigated the efficiencies of Panel-ρ and Group-ρ tests by employing Monte Carlo simulation method, which is usually used to test the heterogeneous panel cointegration relationship. The simulation results indicated that test efficiencies will be influenced under limit sample circumstance with structural change, and its influence is relevant to the type of the structural changes. We developed a Bootstrap cointegration test, which integrates the Continuous-Path Block Bootstrap with these heterogeneous panel cointegration tests, and investigated its efficiency using the Monte Carlo simulation method. The results show that the proposed method can obviously improve the efficiency of panel cointegration test with structural changes. Finally, as an example, we conducted the Bootstrap cointegration test to the panel data of GDP and FDI, it is found that GDP and FDI of the coastal regions in China have the panel cointegration relationship with structural changes.

关 键 词：面板数据 自举法 结构变化 蒙特卡罗模拟 

分 类 号：F224.0[经济管理—国民经济]