非线性测量误差模型的影响分析(英文)  

Influence Analysis on Nonlinear Measurement Error Models

作　　者：宗序平[1] 孟国明[1] 王海斌[2] 韦博成[2] 

机构地区：[1]扬州大学数学系,扬州225001 [2]东南大学数学系,南京210018

出　　处：《应用概率统计》2003年第1期31-39,共9页Chinese Journal of Applied Probability and Statistics

基　　金：Project supported by NSFC 40175024 and the grant of Yangzhou University.

摘　　要：本文对非线性测量误差模型给出了统一的诊断方法,并证明了数据删除模型与均值漂移模型的等价性,由此出发得到了Cook距离、残差、杠杆值等诊断统计量.本文还讨论了非线性测量误差模型的局部影响分析,并给出了一个具体应用实例.推广了Zhao & Lee(1995)的结果.In this paper, we present a unified diagnostic method for nonlinear measurement error models. We show that the case deletion model is equivalent to mean shift outlier model. From this point of view, several diagnostic measures, such as Cook distance, Residuals, leverage measures are obtained. The local influence measure of nonlinear measurement errors model is also presented. An numerical example is given to illustrate the application of the diagnostics. The results of Zhao & Lee (1995) are extended.

关 键 词：非线性测量误差模型 COOK距离 局部影响 测量误差 非线性模型 数据删除模型 均值漂移模型 

分 类 号：O212.4[理学—概率论与数理统计]