ASSESSMENT OF INFLUENCE IN NONLINEAR MEASUREMENT ERROR MODELS

被引:9
作者
ZHAO, YJ [1 ]
LEE, AH [1 ]
机构
[1] NO TERR UNIV,FAC SCI,DARWIN,NT 0909,AUSTRALIA
关键词
D O I
10.1080/757584615
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We consider the assessment of outliers and influential observations in nonlinear measurement error models. Residuals, leverage measures and case-deletion diagnostics are examined. The method of local influence is also applied to the models. In particular, the perturbation of measurement error variances has been found useful in assessing the adequacy of the model assumptions. A numerical example is given to illustrate the application of the diagnostics.
引用
收藏
页码:215 / 225
页数:11
相关论文
共 15 条
[1]   DIAGNOSTICS FOR NONLINEARITY AND HETEROSCEDASTICITY IN ERRORS-IN-VARIABLES REGRESSION [J].
CARROLL, RJ ;
SPIEGELMAN, CH .
TECHNOMETRICS, 1992, 34 (02) :186-196
[2]  
Cook R. D., 1987, J APPL STAT, V14, P117, DOI [10.1080/02664768700000016, DOI 10.1080/02664768700000016]
[3]  
COOK RD, 1986, J ROY STAT SOC B MET, V48, P133
[4]  
Fuller Wayne A., 1987, MEASUREMENT ERROR MO, DOI DOI 10.1002/9780470316665
[5]  
HAMPEL FR, 1986, ROBUST STATISTICS AP
[6]   THE INFLUENCE FUNCTION IN THE ERRORS IN VARIABLES PROBLEM [J].
KELLY, G .
ANNALS OF STATISTICS, 1984, 12 (01) :87-100
[7]  
LAWRANCE AJ, 1991, DIRECTIONS ROBUST 1, P141
[8]  
MILLER SM, 1990, STATISTICAL ANAL MEA, P59
[9]  
REILLY PM, 1993, APPL STAT-J ROY ST C, V42, P693
[10]   THE GEOMETRY OF CASE DELETION AND THE ASSESSMENT OF INFLUENCE IN NONLINEAR-REGRESSION [J].
ROSS, WH .
CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, 1987, 15 (02) :91-103