Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Re: Logit and interaction variables


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   stata list <statalist@hsphsun2.harvard.edu>
Subject   st: Re: Logit and interaction variables
Date   Tue, 1 Jun 2010 23:51:15 -0700 (PDT)

"Webb, Natalie" wrote me privately:
> I noted in a Stata post that you said using odds ratios rather than
> marginal effects avoids the problems inteff tries to solve.  I'm
> completely happy to believe you as I'm not an econometrician, but can
> you point me to literature that shows this?  Thanks for your help.

As always when dealing with non-linear models like -logit-, the 
interpretation is influenced by rather subtle distinctions. An odds ratio
is not a marginal effect, the former is a relative (w.r.t. the baseline
odds) measure of the effect size, while the latter is an absolute measure
of the effect size. Both have advantages and disadvantages. One of the 
advantages of odds ratios (and hazard ratios, relative risk ratios, etc.)
is that you can directly interpret the interaction term. I have written
a brief discussion of this, which is about to be published in the Stata
Journal. You can see a pre-publication draft here:
<http://www.maartenbuis.nl/publications/interactions.html>

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/


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