RE: st: asclogit interactions correction

[Liz Lyons <Liz.Lyons09@rotman.utoronto.ca>]

Thanks Maarten, this is very helpful. I have a follow-up question. In your article, you define the base alternative as equal to one for all observations and including the noconstant command. For asclogit, doing this doesn't work because this variable has no within-case variability. I'm wondering if you might know how to define the baseline alternative using asclogit.

Thanks!

Liz

________________________________________
From: owner-statalist@hsphsun2.harvard.edu [owner-statalist@hsphsun2.harvard.edu] on behalf of Maarten Buis [maartenlbuis@gmail.com]
Sent: January-23-12 3:05 AM
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: asclogit interactions correction

On Thu, Jan 19, 2012 at 8:33 PM, Liz Lyons wrote:
> I'm running a regression with interactions using McFadden's choice conditional logit, asclogit, using Stata 11. I'm wondering if there is a command to generate the marginal effects of the interactions, something like the "margins" command for clogit.

-asclogit- gives you odds ratios. With a bit of care you can interpret
the odds ratios without any need of a "correction". See: M.L. Buis
(2010) "Stata tip 87: Interpretation of interactions in non-linear
models", The Stata Journal, 10(2), pp. 305-308.

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/

*
*   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/