A new approach for detecting multivariate outliers

doi:10.1081/STA-200066315

CSpace

	A new approach for detecting multivariate outliers
	Gao, SG ; Li, GY ; Wang, DQ
	2005
发表期刊	COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
ISSN	0361-0926
卷号	34 期号:8 页码:1857-1865
摘要	This article proposes a new procedure named Max-Eigen difference (MED) for identifying outliers in multivariate data sets. Theoretical aspects of the procedure are briefly discussed. The proposed procedure is compared with the Mahalanobis distance (MD) and robust distance (RD) via two examples. It is indicated that the MED works better than MD and is comparable with RD. Finally, this procedure is applied during constructing a quadratic discriminant analysis which is used to splicing sites prediction for DNA sequences. Through the results of rice and human genome data sets, it can be seen that the robustified discriminant provides higher prediction accuracy than the usual discrimination method.
关键词	donor Mahalanobis distance MED outlier robust distance
DOI	10.1081/STA-200066315
语种	英语
WOS研究方向	Mathematics
WOS类目	Statistics & Probability
WOS记录号	WOS:000231271900013
出版者	TAYLOR & FRANCIS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/1495
专题	中国科学院数学与系统科学研究院
通讯作者	Gao, SG
作者单位	1.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100080, Peoples R China 2.Chinese Acad Sci, Beijing Genom Inst, Beijing 100080, Peoples R China 3.Victoria Univ Wellington, Sch Math & Comp Sci, Wellington, New Zealand
推荐引用方式 GB/T 7714	Gao, SG,Li, GY,Wang, DQ. A new approach for detecting multivariate outliers[J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS,2005,34(8):1857-1865.
APA	Gao, SG,Li, GY,&Wang, DQ.(2005).A new approach for detecting multivariate outliers.COMMUNICATIONS IN STATISTICS-THEORY AND METHODS,34(8),1857-1865.
MLA	Gao, SG,et al."A new approach for detecting multivariate outliers".COMMUNICATIONS IN STATISTICS-THEORY AND METHODS 34.8(2005):1857-1865.