Canonical+Correlation

Canonical Correlation (Multivariate Methods) (GWU EMSE-271)
Index | Topics (Logical Lectures) | Lectures | Problems | Readings | Nomenclature | Concepts

"In statistics, **canonical correlation analysis**, introduced by Harold Hotelling, is a way of making sense of cross-covariance matrices. If we have two sets of variables, and there are correlations among the variables, then canonical correlation analysis will enable us to find linear combinations which have maximum correlation with each other." - [|Wikipedia]

"Like principal components, canonical correlation helps reduce the dimensionality of the problem." - Lattin

"In statistics, the **generalized canonical correlation analysis** (gCCA), is a way of making sense of cross-correlation matrices between the sets of random variables when there are more than two sets. It is a generalization of the Principal component analysis (PCA) to more than two sets of random variables like a conventional CCA also does the same thing for only two sets. The **canonical variables** represent those **common factors** that can be found by a large PCA of all of the transformed random variables after each set underwent its own PCA." - [|Wikipedia]

"... multiple analysis of variance" ... " is a special case of canonical correlation." - Lattin


 * Sources:**
 * Canonical correlation. (2009, September 16). In //Wikipedia, The Free Encyclopedia//. Retrieved 15:53, December 2, 2009, from []
 * Analyzing Multivariate Data, by James Lattin, Douglas Carroll and Green ([|Amazon]), page 14
 * Generalized canonical correlation. (2008, March 18). In //Wikipedia, The Free Encyclopedia//. Retrieved 15:54, December 2, 2009, from []