时空地理加权回归模型的统计诊断  

Statistical Diagnostics for Spatial-Temporal Geographical Weighted Regression Model

作　　者：刘美玲[1] 王博[1] 张雪敏[1] 

机构地区：[1]西安建筑科技大学理学院,西安710055

出　　处：《西安文理学院学报（自然科学版）》2013年第2期35-39,共5页Journal of Xi’an University(Natural Science Edition)

摘　　要：时空地理加权回归模型作为一类能简单有效的解决数据时空特性问题的数据分析方法已经得到了广泛的应用.主要研究该模型的统计诊断与影响分析.首先,基于数据删除模型定义了Cook统计量;其次,基于均值漂移模型讨论了异常点的检验问题,并构造了相应的检验统计量.As a spatial data analysis method, Spatial -Temporal Geographical Weighted Re- gression Model is effective and simple to address the spatial and temporal features of data and therefore has a wide application. In this paper, we mainly discuss the statistical diagnostics and influence analysis on this model. Firstly, Cook statistic based on data deletion model is intro- duced ; secondly, based on the mean shift model, the testing of a given observation is discussed and the corresponding test statistic is constructed.

关 键 词：时空地理加权回归模型 COOK距离 均值漂移模型 

分 类 号：O212[理学—概率论与数理统计]