Universität zu Köln

Lange, Tatjana, Mosler, Karl and Mozharovskyi, Pavlo (2014). Fast nonparametric classification based on data depth. Stat. Pap., 55 (1). S. 49 - 70. NEW YORK: SPRINGER. ISSN 1613-9798

Full text not available from this repository.

Abstract

A new procedure, called D D alpha-procedure, is developed to solve the problem of classifying d-dimensional objects into q a parts per thousand yen 2 classes. The procedure is nonparametric; it uses q-dimensional depth plots and a very efficient algorithm for discrimination analysis in the depth space [0,1] (q) . Specifically, the depth is the zonoid depth, and the algorithm is the alpha-procedure. In case of more than two classes several binary classifications are performed and a majority rule is applied. Special treatments are discussed for 'outsiders', that is, data having zero depth vector. The D D alpha-classifier is applied to simulated as well as real data, and the results are compared with those of similar procedures that have been recently proposed. In most cases the new procedure has comparable error rates, but is much faster than other classification approaches, including the support vector machine.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Lange, Tatjana UNSPECIFIED UNSPECIFIED UNSPECIFIED Mosler, Karl UNSPECIFIED UNSPECIFIED UNSPECIFIED Mozharovskyi, Pavlo UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-447227
DOI:	10.1007/s00362-012-0488-4
Journal or Publication Title:	Stat. Pap.
Volume:	55
Number:	1
Page Range:	S. 49 - 70
Date:	2014
Publisher:	SPRINGER
Place of Publication:	NEW YORK
ISSN:	1613-9798
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language Statistics & Probability Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/44722