s-news
[Top] [All Lists]

gap statistic

To: "s-plus.list" <s-news@lists.biostat.wustl.edu>
Subject: gap statistic
From: Kamil Toth <kamiltoth@yahoo.com>
Date: Wed, 17 Nov 2004 13:07:07 -0800 (PST)
Comment: DomainKeys? See http://antispam.yahoo.com/domainkeys
Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; b=OqUcZFjqALvwC///JjBrHjwlREpPOQmhehpgfh4T/yzGykeXrPDzBRwB2rHdQNLNMxTDu4FNxhZpV6iTPaLq1Ib+0WXE4/9ydHCnIGfH/nnHBjUxV7iIIgXhLKAkMcSXo0Av398z8eW/D7bFM+Psop36YGnErJEsUzG5ONyqako= ;
Folks:
Is there an S+ function to compute the GAP statistic by Tibshirani et al for estimating the number of clusters? Is it better than the "silhouette" statistic?
Thanks
 
Kamil Toth
Ecole Normale Superier
Paris, France


Do you Yahoo!?
Meet the all-new My Yahoo! ? Try it today!
<Prev in Thread] Current Thread [Next in Thread>
  • gap statistic, Kamil Toth <=