Detecting outliers and influential points: an indirect classical Mahalanobis distance-based method

Detecting outliers and influential points: an indirect classical Mahalanobis distance-based method
复制标题

检测异常值和影响点:基于间接经典马氏距离的方法

DOI:
10.1080/00949655.2018.1448981
复制
发表时间:
2018-03
影响因子:
1.2
通讯作者:
Zhiguo Zhao
Zhiguo Zhao
中科院分区:
数学4区
文献类型:
--
作者:
Xuqing Liu;Feng Gao;Y;ong Wu;Zhiguo Zhao

文献摘要

参考文献

相似文献

本文考虑了异常点和影响点的检测问题,提出了一种间接的基于马氏距离的多变量数据集检测方法(ICMD)。Escherseuw和货车Zomeren将离群值描述为不遵循大多数数据模式的点;这种描述在统计学文献中被普遍接受。首先,我们通过整合以下思想来更新此描述以构建ICMD:数据驱动模式中至少一个点的作用在排除离群值之前和之后都会受到很大影响。然后,使用类似的想法来识别影响点。给出了具体的算法。两个人工数据集和三个真实的数据集的应用表明,ICMD是强大的,沼泽,抗掩蔽。
ABSTRACT In this paper, we consider the problem of detecting outliers and influential points and propose an indirect classical Mahalanobis distance-based method (ICMD) for multivariate datasets. Rousseeuw and Van Zomeren described outliers as those points that do not follow the pattern of the majority of the data; this description has been commonly accepted in the statistical literature. First, we update this description to build ICMD by integrating the following idea: the role of at least one point in the data-driven pattern will be affected greatly before and after excluding an outlier. Then, a similar idea is used to identify influential points. The resulting algorithms are given in detail. Two artificial datasets and three real datasets are applied to show that ICMD is robust, swamping-free, and masking-resistant.
DOI: 10.1080/03610910701812352
发表时间: 2008-01-01
影响因子: 0.9
作者:
Billor, Nedret;Kiral, Gulsen
通讯作者: Kiral, Gulsen
DOI: 10.1080/02664760802553463
发表时间: 2009-05
影响因子: 1.5
作者:
M. Habshaha;M. R. Norazanb;Rahmatullah Imonc
通讯作者: M. Habshaha;M. R. Norazanb;Rahmatullah Imonc
DOI: 10.1142/6986
发表时间: 2009-06
期刊: --
影响因子: --
作者:
Xin Yan;Xiaogang Su
通讯作者: Xin Yan;Xiaogang Su
DOI: 10.1007/978-0-387-09823-4_7
发表时间: 2010-01-01
期刊: DATA MINING AND KNOWLEDGE DISCOVERY HANDBOOK, SECOND EDITION
影响因子: --
作者:
Ben-Gal, Irad
通讯作者: Ben-Gal, Irad
DOI: 10.1016/j.chemolab.2004.08.001
发表时间: 2020-08
期刊: Cytokine
影响因子: 3.8
作者:
M. Velden;Patrick J. F. Groenen;Jeroen Poblome
通讯作者: M. Velden;Patrick J. F. Groenen;Jeroen Poblome