eprintid: 20822
rev_number: 15
eprint_status: archive
userid: 2326
dir: disk0/00/02/08/22
datestamp: 2016-06-02 07:55:23
lastmod: 2016-07-19 11:39:48
status_changed: 2016-06-02 07:55:23
type: article
metadata_visibility: show
creators_name: Mammen, Enno
creators_name: Tsybakov, Alexandre B.
title: Smooth Discrimination Analysis
subjects: ddc-310
subjects: ddc-510
divisions: i-110400
keywords: Discrimination analysis, optimal rates, empirical risk, Bayes risk, sieves
abstract: Discriminant analysis for two data sets in R^d with probability densities f and gcan be based on the estimation of the set G = { x : f(x) > = g(x) }. Weconsider applications where it is appropriate to assume that the regionG has a smooth boundary. In particular, this assumption makes sense if discriminant analysis is used as a data analytic tool. We discussoptimal rates for estimation of G.
date: 1999
publisher: IMS Business Office
id_scheme: DOI
id_number: 10.11588/heidok.00020822
official_url: http://projecteuclid.org/euclid.aos/1017939240
schriftenreihe_cluster_id: sr-10a
schriftenreihe_order: 44
ppn_swb: 1657259862
own_urn: urn:nbn:de:bsz:16-heidok-208222
language: eng
bibsort: MAMMENENNOSMOOTHDISC1999
full_text_status: public
publication: The Annals of Statistics
volume: 27
number: 6
place_of_pub: Hayward, California
pagerange: 1808-1829
issn: 0090-5364
citation:   Mammen, Enno ; Tsybakov, Alexandre B.  (1999) Smooth Discrimination Analysis.  The Annals of Statistics, 27 (6).  pp. 1808-1829.  ISSN 0090-5364     
document_url: https://archiv.ub.uni-heidelberg.de/volltextserver/20822/1/beitrag.44.pdf