CLASS-L Archives

October 2000

CLASS-L@LISTS.SUNYSB.EDU

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Zdenek Skala <[log in to unmask]>
Reply To:
Classification, clustering, and phylogeny estimation
Date:
Tue, 10 Oct 2000 09:20:17 +0100
Content-Type:
text/plain
Parts/Attachments:
text/plain (19 lines)
Basavanneppa Tallur wrote:
> I don't know if someone has answered your query. I work in the area of
> cluster analysis methodology and its applications and I can tell you that
> you don't have to bother about the correlated variables in your data set;
> it has no side effects on your results.

? - If I understand it well, there was a worry that correlated variables
measure the same "thing"; something like including body volume
and body weight in the cluster analysis. If the same "thing" is
measured by several variables that are treated as independent, it
will of course distort euclidean distance matrix. The question was -
in my understanding - raised how to adjust for in such cases.
Best!
Zdenek
++++++++++++++++++++++
] Zdenek Skala
] e-mail:
] [log in to unmask]

ATOM RSS1 RSS2