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]

Re: st: Binary Choice Model and fixed effects - interpreting the interaction effects?


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Binary Choice Model and fixed effects - interpreting the interaction effects?
Date   Mon, 2 Apr 2012 12:35:57 +0200

On Mon, Apr 2, 2012 at 12:19 PM, Benjamin Niug wrote:
> @Maarten: Thanks for the odds ratio hint. Do you know of other
> solutions as well?

No, because there is none (IMHO). The problem with marginal effects is
that they in essence fit a linear model on top of your non-linear
(-clogit-) model. This is fine as long as your model is simple enough
so that the linear model is an adequate approximation of your
non-linear model. As soon as you are making your model more complex
(by adding fixed effects or interactions), this solution starts
breaking down. In that case you need to add fix upon fix. Once you
start fixing the fix, that that is a clear sign that you need to stop
what you are doing and rethink your approach.

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