Next: Example of Multiple
Up: 3: Estimation of
Previous: Interpretation of Value
- Note that if
are calculated from the same population,
e.g.,
- Then they are not independent,
- but we can use the theorem proved at the end of Section 2 to show
that
will (for large m) be Gaussian.
- However, there is a correlation matrix, i.e.,
as discussed in Solmitz.
- By diagonalizing M we can (in principle) reduce this to the
usual
method with 
replaced by eigenvectors of M.
Geoffrey Fox, Northeast Parallel Architectures Center at Syracuse University, gcf@npac.syr.edu