Discriminant analysis for compositional data and robust parameter estimation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15310%2F12%3A33140618" target="_blank" >RIV/61989592:15310/12:33140618 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/s00180-011-0279-8" target="_blank" >http://dx.doi.org/10.1007/s00180-011-0279-8</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/s00180-011-0279-8" target="_blank" >10.1007/s00180-011-0279-8</a>
Alternative languages
Result language
angličtina
Original language name
Discriminant analysis for compositional data and robust parameter estimation
Original language description
Compositional data, i.e. data including only relative information, need to be transformed prior to applying the standard discriminant analysis methods that are designed for the Euclidean space. Here it is investigated for linear, quadratic, and Fisher discriminant analysis, which of the transformations lead to invariance of the resulting discriminant rules. Moreover, it is shown that for robust parameter estimation not only an appropriate transformation, but also affine equivariant estimators of location and covariance are needed. An example and simulated data demonstrate the effects of working in an inappropriate space for discriminant analysis.
Czech name
—
Czech description
—
Classification
Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
BB - Applied statistics, operational research
OECD FORD branch
—
Result continuities
Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Computational statistics
ISSN
0943-4062
e-ISSN
—
Volume of the periodical
27
Issue of the periodical within the volume
4
Country of publishing house
DE - GERMANY
Number of pages
20
Pages from-to
585-604
UT code for WoS article
000310379900001
EID of the result in the Scopus database
—