空间滞后模型的标准化稳健检验及其功效对比分析  

Standardized robust LM test for spatial lag model and efficiency analyses

作　　者：钱争鸣[1] 刘立虎[1] 

机构地区：[1]厦门大学经济学院统计系,厦门361005

出　　处：《系统工程理论与实践》2014年第5期1137-1144,共8页Systems Engineering-Theory & Practice

基　　金：国家社会科学基金(08BZY076);国家自然科学基金(71073131);教育部重点研究基地重大项目(12JJD790027);福建省自然科学基金重点项目(2009R0074)

摘　　要：在误差项分布未知、模型设定偏误以及不同形式空间布局的复杂条件下,本文提出检验空间滞后模型的标准化稳健LM检验方法,并采用Bootstrap法和Monte Carlo法对统计量的渐进性进行分析.结果表明:采用Bootstrap法和Monte Carlo法的检验功效均优于现有LM检验方法;对于小样本,结合Bootstrap法与本文提出的统计量进行模型设定的检验更可靠;在空间布局为Group规则时,采用本文提出的统计量进行模型设定的检验效果更好.This paper proposes a new robust LM test for spatial lag model that is set when there are un- known error distribution, model misspecification and changes of spatial layout. We analyze the asymptotic properties using Bootstrap and Monte Carlo methods which are found to be superior to the LM method. Moreover, we also find that Bootstrap is most efficacious. It is more reliable to use combined Bootstrap and our proposed testing statistic when sample size is small. It is also more reliable to use our proposed testing statistic when ＂Group＂ in spatial layouts is contiguous.

关 键 词：未知分布 空间布局 模型设定 标准化稳健检验 BOOTSTRAP法 

分 类 号：F224.0[经济管理—国民经济]