Outlier detection and accommodation in general spatial models |
| |
Authors: | Xiaowen?Dai Libin?Jin Anqi?Shi Email author" target="_blank">Lei?ShiEmail author |
| |
Institution: | 1.School of Statistics,Renmin University of China,Beijing,China;2.College of Letters and Science,University of Wisconsin-Madison,Madison,USA;3.School of Statistics and Mathematics,Yunnan University of Finance and Economics,Kunming,China |
| |
Abstract: | This paper studies outlier detection and accommodation in general spatial models including spatial autoregressive models and spatial error model as special cases. Using mean-shift and variance-weight models respectively, test statistics for multiple outliers are derived and the detecting procedures are proposed. In addition, several key diagnostic measures such as standardized residuals and leverage measure are defined in general spatial models. Outlier modified models are proposed to accommodate outliers in the data set. The performance of test statistics, including size and power, are examined via simulation studies. Three real examples are analyzed and the results show that the proposed methodology is useful for identifying and accommodating outliers in general spatial models. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|