==================================================================
The gateway between this list and the sci.stat.edu newsgroup will
be disabled on June 9.  This list will be discontinued on June 21.
Subscribe to the new list EDSTAT-L at Penn State using the web
interface at http://lists.psu.edu/archives/edstat-l.html.
==================================================================
.

On  8-Jun-2004, [EMAIL PROTECTED] (=?iso-8859-1?q?juan=20carlos?=)
wrote:

> I should highly appreciate it if some one could advice
> me on how to do with this issue: I have been trying to
> categorise a continuous variable which is the total
> assets of a 295 company. The problem is that there are
> few clusters (of very few firms each) located a way
> from the highest percentiles. What I meant is that
> there is a huge gap between the very large ones and
> few others in the middle of the range the very vast
> majority of the sample. This made the categorisation
> quite cumbersome.

What is the goal of the categorization?  Are you trying to predict and
explain the categories as a function of other (predictor) variables, or are
you just trying to cluster similar values?

-- 
Phil Sherrod
(phil.sherrod 'at' sandh.com)
http://www.dtreg.com  (decision tree modeling)
http://www.nlreg.com  (nonlinear regression)

Reply via email to