Rich Ulrich <[EMAIL PROTECTED]> wrote:
: I can believe someone would call it that, but I can believe other
: tests would be called that, too. You state this is, in reference
: to what test (what computer program, or what textbook)?
see my other post
: MANOVA is a canonical correlation problem. MANCOVA, so far
: as I imagine it, is another canonical correlation problem. You might
: be taking steps in a particular order, but you are still solving
: to find the eigenvalues of an asymmetric matrix -- at least,
: most of the time.
Yes; they are both CC problems, one with dummy variables on one side, the
other with dummys and continuous on one side. The assymmetric matrix is
transformed to a symmetric matrix for solution
The two formulations of the problem are
Sh x = kSe x Manova x an eigenvector
Sh x = c(Sh+Se) x CanR
Factoring the Sh show that x is the same in both cases but
c = k/(1+k)
so that the problems are equivalent
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
