Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: stepwise regression


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: stepwise regression
Date   Tue, 13 Apr 2004 17:10:58 +0100

I don't know what other listservers you
follow, but we had one such thread recently
on Statalist, starting a week ago, and the topic is recurrent. 

In most cases, each thread is a constant (reference 
to the Bill Sribney FAQ and the Frank Harrell book)
plus a variable (e.g. Ronán Conroy's spirited 
reply last Tuesday). 

If more people read the archives, as you suggest,
and also the FAQ, then such threads might not occur: 
a mixed blessing given the animosity which stepwise
procedures attract and the cathartic effect of fulminating
against them. 

Nick 
n.j.cox@durham.ac.uk 

Jim.Seward@sunhealth.org
 
> I forget if it was on this listserver or another, but there was an
> interesting thread recently on the problems with automated regression
> procedures, such as best subsets and stepwise.  You may want 
> to look in the
> archives to see if it was on this list.

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index