Publication
Title
Detecting influential observations in Kernel PCA
Author
Abstract
Kernel Principal Component Analysis extends linear PCA from a Euclidean space to any reproducing kernel Hilbert space. Robustness issues for Kernel PCA are studied. The sensitivity of Kernel PCA to individual observations is characterized by calculating the influence function. A robust Kernel PCA method is proposed by incorporating kernels in the Spherical PCA algorithm. Using the scores from Spherical Kernel PCA, a graphical diagnostic is proposed to detect points that are influential for ordinary Kernel PCA.
Language
English
Source (journal)
Computational statistics and data analysis / International Association for Statistical Computing. - Amsterdam, 1983, currens
Publication
Amsterdam : North-Holland , 2010
ISSN
0167-9473 [print]
1872-7352 [online]
Volume/pages
54 :12 (2010) , p. 3007-3019
ISI
000281333900011
Full text (Publisher's DOI)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Web of Science
Record
Identifier
Creation 20.10.2010
Last edited 25.05.2022
To cite this reference