Depth-Based Classification for Distributions with Nonconvex Support

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F13%3A10173473" target="_blank" >RIV/00216208:11320/13:10173473 - isvavai.cz</a>

Alternative codes found

RIV/61989592:15310/13:33157689

Result on the web

<a href="http://www.hindawi.com/journals/jps/2013/629184/" target="_blank" >http://www.hindawi.com/journals/jps/2013/629184/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1155/2013/629184" target="_blank" >10.1155/2013/629184</a>

Result language

angličtina

Original language name

Depth-Based Classification for Distributions with Nonconvex Support

Original language description

Halfspace depth became a popular nonparametric tool for statistical analysis of multivariate data during the last two decades. One of applications of data depth considered recently in literature is the classification problem. The data depth approach is used instead of the linear discriminant analysis mostly to avoid the parametric assumptions and to get better classifier for data whose distribution is not elliptically symmetric, for example, skewed data. In our paper, we suggest to use weighted versionof halfspace depth rather than the halfspace depth itself in order to obtain lower misclassification rate in the case of "nonconvex" distributions. Simulations show that the results of depth-based classifiers are comparable with linear discriminant analysis for two normal populations, while for nonelliptic distributions the classifier based on weighted halfspace depth outperforms both linear discriminant analysis and classifier based on the usual (nonweighted) halfspace depth.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

BA - General mathematics

OECD FORD branch

—

Project

<a href="/en/project/EE2.3.20.0170" target="_blank" >EE2.3.20.0170: Building of Research Team in the Field of Environmental Modeling and the Use of Geoinformation Systems with the Consequence in Participation in International Networks and Programs</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2013

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Journal of Probability and Statistics

ISSN

1687-952X

e-ISSN

—

Volume of the periodical

2013

Issue of the periodical within the volume

September

Country of publishing house

EG - EGYPT

Number of pages

7

Pages from-to

1-7

UT code for WoS article

—

EID of the result in the Scopus database

—