Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Removing coefficients from model with highest p-values
From
Melissa Barnett <[email protected]>
To
[email protected]
Subject
Re: st: Removing coefficients from model with highest p-values
Date
Thu, 03 Mar 2011 09:46:30 -0500
Thank you very much for both the information on stepwise and the
direction on why it's not the best approach....Melissa
On 3/3/2011 3:38 AM, Maarten buis wrote:
--- On Wed, 2/3/11, Melissa Barnett wrote:
I have a model that includes the main effects and every
possible combination for 2-way interactions between the
main effects. I've started with this model and then after
it has completed running, I manually remove the
interaction with the highest p-value and then re-run the
model again until all of the interaction effects left in
the model are significant. Is there a way in Stata to do
this without having to manually remove the term with the
highest p-value?
First of all there are many reasons why you should not
do this:
<http://www.stata.com/support/faqs/stat/stepwise.html>
But if you still insist you can look at -help stepwise-.
But let me repeat: do not do it.
Hope this helps,
Maarten
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://www.maartenbuis.nl
--------------------------
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
--
Melissa D. Barnett, Ph.D.
Research Analyst, FICSMath
Science Education Department
Harvard-Smithsonian Center for Astrophysics
60 Garden Street, MS71
Cambridge, MA 02138
617-496-9070
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/