The Open UniversitySkip to content
 

A clustering approach to interpretable principal components

Enki, Doyo G.; Trendafilov, Nickolay T. and Jolliffe, Ian T. (2013). A clustering approach to interpretable principal components. Journal of Applied Statistics, 40(3) pp. 583–599.

Full text available as:
Full text not publicly available (Version of Record)
Due to publisher licensing restrictions, this file is not available for public download
Click here to request a copy from the OU Author.
DOI (Digital Object Identifier) Link: https://doi.org/10.1080/02664763.2012.749846
Google Scholar: Look up in Google Scholar

Abstract

A new method for constructing interpretable principal components is proposed. The method first clusters the variables, and then interpretable (sparse) components are constructed from the correlation matrices of the clustered variables. For the first step of the method, a new weighted-variances method for clustering variables is proposed. It reflects the nature of the problem that the interpretable components should maximize the explained variance and thus provide sparse dimension reduction. An important feature of the new clustering procedure is that the optimal number of clusters (and components) can be determined in a non-subjective manner. The new method is illustrated using well-known simulated and real data sets. It clearly outperforms many existing methods for sparse principal component analysis in terms of both explained variance and sparseness.

Item Type: Journal Item
Copyright Holders: 2012 Taylor & Francis
ISSN: 1360-0532
Keywords: sparse principal components; clustering variables; eigenvalues; weighted variances; interpretation
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Mathematics and Statistics
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Item ID: 35928
Depositing User: Nickolay Trendafilov
Date Deposited: 02 Jan 2013 09:45
Last Modified: 10 Dec 2018 04:52
URI: http://oro.open.ac.uk/id/eprint/35928
Share this page:

Metrics

Altmetrics from Altmetric

Citations from Dimensions

Actions (login may be required)

Policies | Disclaimer

© The Open University   contact the OU