Canonical Correlation and Its Relationship to Discriminant Analysis and Multiple Regression

by: Harry R Glahn

Journal of the Atmospheric Sciences, Vol. 25, No. 1. (1 January 1968), pp. 23-31.

View FullText article

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

vrich

Find related articles with these CiteULike tags

canonical_correlation_analysis

Abstract

Canonical correlation analysis is concerned with the determination of a linear combination of each of two sets of variables such that the correlation between the two functions is a maximum. Under certain conditions this analysis is equivalent to discriminant analysis and under other conditions it is equivalent to multiple regression. In this paper the relationships among these techniques are discussed, equations relating to prediction by canonical variates are derived, a generalized correlation coefficient is proposed, and an example of canonical correlation analysis is presented.

@article{citeulike:2774015, abstract = {Canonical correlation analysis is concerned with the determination of a linear combination of each of two sets of variables such that the correlation between the two functions is a maximum. Under certain conditions this analysis is equivalent to discriminant analysis and under other conditions it is equivalent to multiple regression. In this paper the relationships among these techniques are discussed, equations relating to prediction by canonical variates are derived, a generalized correlation coefficient is proposed, and an example of canonical correlation analysis is presented.}, author = {Glahn, Harry R. }, citeulike-article-id = {2774015}, doi = {10.1175/1520-0469(1968)025<0023:CCAIRT>2.0.CO;2}, journal = {Journal of the Atmospheric Sciences}, keywords = {canonical\_correlation\_analysis}, month = {January}, number = {1}, pages = {23--31}, posted-at = {2008-05-09 03:53:50}, priority = {2}, title = {Canonical Correlation and Its Relationship to Discriminant Analysis and Multiple Regression}, url = {http://dx.doi.org/10.1175/1520-0469(1968)025\%3C0023:CCAIRT\%3E2.0.CO;2}, volume = {25}, year = {1968} }

RIS record

TY - JOUR ID - citeulike:2774015 L3 - citeulike-article-id:2774015 TI - Canonical Correlation and Its Relationship to Discriminant Analysis and Multiple Regression JF - Journal of the Atmospheric Sciences VL - 25 IS - 1 SP - 23 EP - 31 N2 - Canonical correlation analysis is concerned with the determination of a linear combination of each of two sets of variables such that the correlation between the two functions is a maximum. Under certain conditions this analysis is equivalent to discriminant analysis and under other conditions it is equivalent to multiple regression. In this paper the relationships among these techniques are discussed, equations relating to prediction by canonical variates are derived, a generalized correlation coefficient is proposed, and an example of canonical correlation analysis is presented. KW - canonical_correlation_analysis AU - Glahn, Harry PY - 1968/01/01/ UR - http://dx.doi.org/10.1175/1520-0469(1968)025%3C0023:CCAIRT%3E2.0.CO;2 ER -

RIS BibTeX