|
Title
|
|
|
|
Robust principal component analysis based on pairwise correlation estimators
|
|
|
Author
|
|
|
|
|
|
|
Abstract
|
|
|
|
| Principal component analysis tries to explain and simplify the structure of multivariate data. For standardized variables, these principal components correspond to the eigenvectors of their correlation matrix. To obtain a robust principal components analysis, we estimate this correlation matrix componentwise by using robust pairwise correlation estimates. We show that the approach based on pairwise correlation estimators does not need a majority of outlier-free observations which becomes very useful for high dimensional problems. We further demonstrate that the "bivariate trimming" method especially works well in this setting. |
|
|
|
Language
|
|
|
|
English
|
|
|
Source (journal)
|
|
|
|
COMPSTAT'2010: 19TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL STATISTICS
|
|
|
Source (book)
|
|
|
|
19th International Conference on Computational Statistics, (COMPSTAT'2010), AUG 22-27, 2010, Paris, FRANCE
|
|
|
Publication
|
|
|
|
Heidelberg
:
Physica-verlag gmbh & co
,
2010
|
|
|
ISBN
|
|
|
|
978-3-7908-2603-6
|
|
|
DOI
|
|
|
|
10.1007/978-3-7908-2604-3_59
|
|
|
Volume/pages
|
|
|
|
(2010)
, p. 573-580
|
|
|
ISI
|
|
|
|
000395720500059
|
|
|
Full text (Publisher's DOI)
|
|
|
|
|
|
|
Full text (publisher's version - intranet only)
|
|
|
|
|
|