| Home | E-Submission | Sitemap | Editorial Office |  
top_img
Journal of Korean Society for Quality Management > Volume 23(4); 1995 > Article
Journal of Korean Society for Quality Management 1995;23(4): 28-.
다변량 자료에서 다수 이상치 인식의 절차
염준근1, 박종구2, 김종우3
1동국대학교 통계학과
2원광대학교 컴퓨터공학과
3제주교육대학교 수학교육과
A Procedure for Indentifying Outliers in Multivariate Data
Joon-Keun Yum1, Jong-Goo Park2, Jong-Woo Kim3
1Dept. of Statistics, Dongguk University
2Dept. of Computer Science, Wonkwang University
3Dept. of Mathematics Education, Cheju National University
ABSTRACT
We consider the problem of identifying multiple outliers in linear model. The available regression diagnostic methods often do not succeed in detecting multiple outliers because of the masking and swamping effect. Recently, among the various robust estimator of reducing the effect of outliers, LMS(Least Meadian Square) estimator has been to be a suitable method proposed to expose outliers and leverage points. However, as you know it, the data analysis method with LMS estimator is to be taken the median of the squared residuals in the sample which is extracted the sample space. Then this model causes the trouble, for the number of the chosen sample is nCp, i.e. as the size of sample space n is increasing, the number is increasing fastly. And the covariance matrix may be the singular matrix, so that matrix is approching collinearity. Thus we propose a procedure ELMS for the resampling in LMS method and study the size of the effective elementary set in this algorithm.
TOOLS
PDF Links  PDF Links
Full text via DOI  Full text via DOI
Download Citation  Download Citation
Share:      
METRICS
1,255
View
4
Download
Related articles
Outward Testing Procedure for the Identification of Multiple Outliers  1996 ;24(3)
An AHP Procedure for Selecting the Best Facility under Uncertain Cost Attributes  1994 ;22(3)
Editorial Office
1806, 310, Gangnam-daero, Gangnam-gu, Seoul, 06253, Korea
TEL: +82-2-563-0357   FAX: +82-2-563-0358   E-mail: ksqmeditor@ksqm.org
About |  Browse Articles |  Current Issue |  For Authors and Reviewers
Copyright © The Korean Society for Quality Management.                 Developed in M2PI
Close layer
prev next