Lubbe-Gardner, Sugnet; le Roux, Niël J. and Gower, John C.
(2008).
| DOI (Digital Object Identifier) Link: | https://doi.org/10.1080/02664760802185399 |
|---|---|
| Google Scholar: | Look up in Google Scholar |
Abstract
Treating principal component analysis (PCA) and canonical variate analysis (CVA) as methods for approximating tables, we develop measures, collectively termed predictivity, that assess the quality of fit independently for each variable and for all dimensionalities. We illustrate their use with data from aircraft development, the African timber industry and copper froth measurements from the mining industry. Similar measures are described for assessing the predictivity associated with the individual samples (in the case of PCA and CVA) or group means (in the case of CVA). For these measures to be meaningful, certain essential orthogonality conditions must hold that are shown to be satisfied by predictivity.
| Item Type: | Journal Item |
|---|---|
| Copyright Holders: | 2008 Taylor & Francis |
| ISSN: | 1360-0532 |
| Extra Information: | Winner of the Gopal Kanji Prize 2008 |
| Keywords: | biplots; canonical variate analysis; measures of fit; prediction; principal component analysis |
| Academic Unit/School: | Faculty of Science, Technology, Engineering and Mathematics (STEM) > Mathematics and Statistics Faculty of Science, Technology, Engineering and Mathematics (STEM) |
| Item ID: | 22530 |
| Depositing User: | Sarah Frain |
| Date Deposited: | 18 Aug 2010 11:13 |
| Last Modified: | 02 May 2018 13:14 |
| URI: | http://oro.open.ac.uk/id/eprint/22530 |
| Share this page: |     |
Metrics
Altmetrics from Altmetric | Citations from Dimensions |
CORE (COnnecting REpositories)
CORE (COnnecting REpositories)