In a dataset with multiple continuous variables we calculate
the multivariate distance of individuals. The original axes are used to
derive new linear combinations based on the correlational structure of
variables.
Use
file "mmreg.csv", and divide the variables into measuring psychological traits and academic abilities
Using library CCA obtain correlation matrices within and between the two sets of variables
Calculate the canonical correlation between the two sets of variables. columns 3 and 4 contain the x and y coefficients
Test for significance of the
number of dimensions. This is not available in a single package and
needs to be calculated. To do this first intialize a couple of the
dimensions (with sincere thanks to idre @UCLA)
then perform the basic calculations
then perform and report the tests of significance for the canonical axes
to standardize canonical coefficients for psych SDs
to standardize canonical coefficients for acad SDs
|