On Mon, 22 May 2000 08:46:05 +0200, "Manuel Castejon Limas"
<[EMAIL PROTECTED]> wrote:
> Dear people,
>
> I´m looking for outlier detection methods in non normal multivariate
> distributions.
Looking at outliers from normal, univariate distributions is tough
enough that most people are happy if they manage that. The most that
you can do by applying rules is the identification of scores that are
extreme enough that they are sure to mess up the ANOVA if you stick
with simple analyses.
You want outliers from non-normal? And in the multivariate setting?
That's bold. There is not much that has been used often, that really
makes use of MV settings except for assuming MV normal, and using
Mahanalobis Distance. - that I know of.
Well, you have to place some faith in your metric for each variable,
regardless. Do a nearest-neighbor algorithm, and look for isolates?
--
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
===========================================================================
This list is open to everyone. Occasionally, less thoughtful
people send inappropriate messages. Please DO NOT COMPLAIN TO
THE POSTMASTER about these messages because the postmaster has no
way of controlling them, and excessive complaints will result in
termination of the list.
For information about this list, including information about the
problem of inappropriate messages and information about how to
unsubscribe, please see the web page at
http://jse.stat.ncsu.edu/
===========================================================================
