Analytical rotation in canonical analysis

Simple item page
dc.contributor.authorWong, Eddie Kim
dc.date.accessioned2009-07-15T17:41:34Z
dc.date.available2009-07-15T17:41:34Z
dc.date.issued1990
dc.description.abstractThe present study investigates the viability of analytic rotation as a method in the process of interpreting canonical solutions. Although rotation of canonical components has been proposed as an alternative for the interpretation of canonical analysis and has been applied in some studies, there has been no study having rotation of canonical components as its focus. There has been no systematic study of the various rotation methods and the appropriateness of their use in canonical analysis. Just as the research question and the nature of the data should dictate the analysis, the internal structure of the data should also indicate whether rotation is a viable alternative. In the current study, analytic rotation methods are studied in relationship to different types of data matrices to identify the optimal conditions for rotation. The study found that analytic rotation of canonical variates is a viable method for interpreting results from canonical analysis. Canonical variates should routinely be rotated following the initial solution, as is usually the case with factor analysis. Another conclusion of this study is that a strong theoretical framework can provide the basis for interpretation, and well-defined variables are essential to any factor analysis or canonical analysis.
dc.description.degreePh.D.
dc.identifier.urihttp://hdl.handle.net/10125/9723
dc.languageeng
dc.publisherUniversity of Hawaii at Manoa
dc.relationTheses for the degree of Doctor of Philosophy (University of Hawaii at Manoa). Educational Psychology; no. 2578
dc.rightsAll UHM dissertations and theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission from the copyright owner.
dc.subjectEducational statistics
dc.subjectCanonical correlation (Statistics)
dc.subjectMultivariate analysis
dc.titleAnalytical rotation in canonical analysis
dc.typeThesis
dc.type.dcmiText

Files

Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
uhm_phd_9118069_r.pdf
Size:
2.29 MB
Format:
Adobe Portable Document Format
Description:
Version for non-UH users. Copying/Printing is not permitted
Download
No Thumbnail Available
Name:
uhm_phd_9118069_uh.pdf
Size:
2.26 MB
Format:
Adobe Portable Document Format
Description:
Version for UH users
Download

Collections

Ph.D. - Educational Psychology