NotesFAQContact Us
Search Tips
ERIC Number: ED120234
Record Type: Non-Journal
Publication Date: 1976-Apr
Pages: 20
Abstractor: N/A
Reference Count: N/A
Canonical Analysis as a Generalized Regression Technique for Multivariate Analysis.
Williams, John D.
The use of characteristic coding (dummy coding) is made in showing solutions to four multivariate problems using canonical analysis. The canonical variates can be themselves analyzed by the use of multiple linear regression. When the canonical variates are used as criteria in a multiple linear regression, the R2 values are equal to 0, where 0 is the squared canonical correlation coefficient. Several different methods exist for testing multivariate hypotheses. Where the interest is in a two-way disproportionate multivariate analysis of variance, the trace criterion seems particularly applicable. Characteristic (dummy) coding has been used in multiple linear regression to analyze univariate analysis of variance problems; the same coding scheme can be extended to multiple criteria. While the resulting data are analyzed through canonical analysis, the design matrix conforms to the usual multiple linear regression design matrices. Thus, the utilization of multiple criteria can be pursued in a logical sequence without necessitating continuosly changing the entire terminology. (Author/RC)
Publication Type: Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: N/A
Sponsor: N/A
Authoring Institution: N/A