统计研究 ›› 2011, Vol. 28 ›› Issue (4): 93-98.

• 论文 • 上一篇    下一篇

分布未知情况下的空间滞后模型检验

张进峰   

  • 出版日期:2011-04-15 发布日期:2011-04-14

Spatial Lag Model Test Robust to Unknown Distribution

Zhang Jinfeng   

  • Online:2011-04-15 Published:2011-04-14

摘要: 在扰动项分布未知的情况下,直接采用传统的空间模型检验方法是存在问题的。针对传统空间模型检验方法的不足,本文以Lee和Yu(2010)的研究为基础,采用Lee和Liu(2006)提出的最优矩条件,构造分布未知情况下空间滞后模型的稳健检验统计量。这种检验方法仅需参数的一致估计量,便于计算。蒙特卡罗结果表明,在小样本情况下,本文提出的检验有良好的性质,且明显优于Saavedra(2003)提出的检验。

关键词: 空间滞后模型, MLE估计, GMM估计, 检验

Abstract: It is problematic to use classical spatial model tests under the condition that the distribution is unknown. In view of this fact, this paper constructs a spatial lag model test robust to unknown distribution, based on the theory of Lee and Yu (2010), by using optimal moment conditions proposed by Lee and Liu (2006). This test only needs consistent estimator and is easy to compute. Monte-Carlo simulations show that the test we proposed has good sample property and has an advantage over Saavedra(2003)test.

Key words: Spatial Lag Model, MLE, GMM, Test