Use this url to cite publication: https://hdl.handle.net/20.500.12259/41944
Options
Statistical Estimation of Discriminant Space using Various Projection Indices
Type of publication
Straipsnis kitoje duomenų bazėje / Article in other database (S4)
Title
Statistical Estimation of Discriminant Space using Various Projection Indices
Is part of
Nonlinear Analysis: Modelling and Control. Vilnius : Institute of Mathematics and Informatics, Vol. 6, no. 1 (2001)
Date Issued
Date Issued |
---|
2001 |
Publisher
Vilnius : Institute of Mathematics and Informatics
Is Referenced by
Extent
p. 67-77
Field of Science
Abstract
Projection pursuit is a method for nding interesting projections of high-dimensional multivariate data. Typically interesting projections are found by numerical maximizing some measure of non-normality of projected data (so-called projection index) over projection direction. The problem is to select the index for projection pursuit. In this article we compare performance of ve projection indices: projection indices based on ! 2, 2, Kolmogorov-Smirnov goodness-of- t mea- sures, entropy index and Friedman's index. It is supposed that ob- served random variable satis es a multidimensional Gaussian mixture model.
Type of document
type::text::journal::journal article::research article
Language
Anglų / English (en)
Coverage Spatial
Lietuva / Lithuania (LT)