空间自回归模型的局部影响分析和运用

Local Influence in Spatial Autoregressiom Model and Applications

由于空间数据的相依特性,使得通常的删除点诊断异常值的方法不适合采用。为了寻找数据中的异常点和影响点,采用局部影响分析技术,通过引入扰动的方法来发现影响点,最后通过实例说明局部影响分析技术能够有效地发现模型中可能的影响点,并且能够揭示更多的细节信息。

Spatial autoregression model is one of the commonly used models in spatial data analysis. Due to the complicated dependence structure in the spatial data, the delete - points diagnostics procedure is not suitable for spatial model. In this article, we use the local influence tech to find outliers and influence points in spatial data. An empirical application example is also given to demonstrate powerfulness of our method.