Date: Thu, 24 Feb 2005 23:15:29 -0500
Reply-To: Talbot Michael Katz <topkatz@MSN.COM>
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: Talbot Michael Katz <topkatz@MSN.COM>
Subject: Re: Relative Importance of Explanatory Variables,
Standardized Coefficients, STB option, etc.
Sure, instructive rants, such as yours, rank right up there (I'd say you
had a high standardized coefficient of information, but perhaps I shouldn't
go there...) I haven't seen Kruskal's papers yet (and, by the way, his two
brothers are no slouches, either), but the method you describe of averaging
partial correlations over different orderings sounds worth investigating --
I wonder whether someone has coded this up into a generally available SAS
-- TMK --
"The Macro Klutz"