to amplifiy a bit, the interpretability of regression tends to go down as
the assumptions of normality and homogeneous variance are markedly
different from reality. You can still go through the calcualtions but the
interpretation of results gets tricky. Factor analysis is a sort of
regression
Data mining , by and large, seems to use fairly conventional
multivatiate stats tools along with a bunch of clustering procedures.
In addtion there is a lot of use of neural nets (mostly as a lazy man's
tool or a last resort, but occasionally sensibly). Data prep.
(including transformations)
you may wish to consider NCSS (they have a web site) provides essentially the same
output as SAS but is run from templates not SAS
language. Less expensive, good documentation, excellant support. However does not
provide an audit trail--a necessary feature for
some governmental / legal
Calculation of eigenvalues and eigenvalues requires no assumption.
However evaluation of the results IMHO implicitly assumes at least a
unimodal distribution and reasonably homogeneous variance for the same
reasons as ANOVA or regression. So think of th consequencesof calculating
means and
The earlier responders make some good points but..I have seen plotted
regression lines when the rsquare was 0.005, scatterplots where two
populations were separated by a line that makes a southern gerrrymander
envious, where clusters had fewer than 3 members, etc. etc. The whole thing
would
Dennis: without going into chapter and verse,I think you are touching on sumpin
real. The excitement these days tends to be at interfaces between disciplines
not at the centers of old disciplines. Our academic departments were largely
defined in the 19th century--some have made the
a great spirit. An ornament to the Profession. A person who made all of
our lives easier. A person who wrote with the gusto and spirit of an
enthusiast. A Hero.
Robin Becker wrote:
In article [EMAIL PROTECTED], Petr Kuzmic
[EMAIL PROTECTED] writes
Donald Macnaughton wrote:
John