The Application of the Canonical Correlation Analysis to the Psychological Data

Select Volume / Issue:

• Volume 6,Issue 5, Sept. 2018

Year:

2018

Type of Publication:

Article

Keywords:

Canonical Correlation, Criterion Variable, Predictor Variable, Synthetic Variable

Authors:

Aslayn H. Datu-Dacula; Mark P. Laurente; Janet B. Macoy

Journal:

IJISM

Volume:

6

Number:

5

Pages:

147-149

Month:

September

ISSN:

2347-9051

Abstract:

Many applied behavioral researchers are not aware that there is a general linear model (GLM) that governs most classical univariate such as analysis of variance (ANOVA), regression and multivariate statistical methods. Accordingly, many persons view these statistical methods as separate entities rather than conceptualizing their distinct similarities within the GLM. Canonical correlation analysis (CCA) studies associations between two sets of random variables. CCA represents the highest level of the general linear model (GLM) and can be rather easily conceptualized as a method closely linked with the more widely understood Pearson correlation coefficients r. An understanding of CCA can lead to a more global appreciation of other univariate and multivariate methods in the GLM. Statistics anxiety notwithstanding, the GLM provides a framework for understanding all classical analyses in terms of the simple Pearson r correlation coefficient. The GLM can also be conceptualized as a hierarchal family, with CCA serving as the parent analysis. Contrary to the compartmentalized understanding of statistical methods held by many researchers, CCA subsumes both univariate and multivariate methods as special cases. The researchers demonstrate CCA with basic language, using technical terminology only when necessary for understanding and use of the method. The researchers use psychological data: personality test and intelligence quotient (I.Q.) results, using MANOVA procedure in Statistical Packages for Social Sciences (SPSS) version 14.0. The purpose of this article is to reduce potential statistical barriers and open doors to CCA for applied behavioral scientists and personality researchers

Full text: IJISM_771_FINAL.pdf [Bibtex]