The goal of a canonical correlation analysis (CCA) is to find the linear combinations in two sets of variables that maximize the correlations. By analyzing the variance-covariance structure of these two sets of variables, uncorrelated pairs of linear combinations from the two sets of variables (called canonical variables) are created and their correlations (called canonical correlations) are estimated. CCA serves as a multivariate extension to bivariate correlation analysis and can be used to test for the existence of relationships between two sets of variables.
Canonical Correlation Analysis (CCA)
Files for this workshop are available in Box.
Access FilesA video of this workshop is available at Cornell’s Video on Demand site.
View Video