which maximizes
the differences between the groups in the data according
to a well-defined optimization criterion. Nevertheless CVA cannot
deal with highly collinear data such as spectroscopic data (here
IR spectra) where the number of variables is significantly larger
than the number of samples. Norgaard et al. suggested an alternative
method to solve the problem of singular matrices that results
when analyzing collinear data with CVA. The method, which
named extended CVA (ECVA), is based on the standard CVA and
by a transformation of an eigenvector problem to a regression
problem, it is possible to use PLS in the inner part of CVA thereby
allowing for the analysis of collinear data.