TITLE(cancor @@ Canonical Correlations)
USAGE(
cancor(x, y, xcenter=TRUE, ycenter=TRUE)
)
ARGUMENTS(
ARG(x @@ a matrix containing the x coordinates.)
ARG(y @@ a matrix containing the y coordinates.)
ARG(xcenter @@ a parameter describing any centering to be done
on the x values before the analysis.  The default is substract
the column means, but it is possible to supply a vector of
values to be subtracted from the columns. It is possible to
turn off any adjustment.)
ARG(ycenter @@ like the parameter LANG(xcenter), but for the
y values.)
)
DESCRIPTION(
This function performs a canonical correlation
analysis for the given data.  The analysis seeks
linear combinations of the y variables which are
well explained by linear combinations of the
x variables.
)
VALUES(
A list containing the following components:
@@
ARG(xcoef @@ estimated coefficients for the x variables.)
ARG(ycoef @@ estimated coefficients for the y variables.)
ARG(xcenter @@ the values used to adjust the x variables.)
ARG(ycenter @@ the values used to adjust the x variables.)
)
REFERENCES(
Hotelling H. (1936).
``Relations between two sets of variables''.
ITALIC(Biometrika), BOLD(28), 321-327.
PARA
Seber, G. A. F. (1984).
ITALIC(Multivariate Analysis). New York: Wiley.
)
SEEALSO(
LANG(LINK(qr)), LANG(LINK(svd)).
)
EXAMPLES(
soil <- evap.x[,1:3]
air <- evap.x[,-(1:3)]
airsoil <- cancor(air, soil)
)
