Bookmark and Share

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: margins after mlogit interaction term


From   Richard Williams <richardwilliams.ndu@gmail.com>
To   statalist@hsphsun2.harvard.edu, statalist@hsphsun2.harvard.edu
Subject   Re: st: margins after mlogit interaction term
Date   Fri, 27 Jan 2012 11:28:54 -0500

At 11:19 AM 1/27/2012, Ida Hansen wrote:
I'm using Stata 12. I'm using margins after mlogit. I have an interaction
term in the model. I have read that the old mfx command gave incorrect
results for interaction effects, while the new margins command gives you no
results. However, I got results for the interaction terms (country*gender)
using margins after mlogit, and I suppose therefore that I have done
something wrong. How can I estimate correct interaction terms in
multinominal logistic regression?

Example for outcome 1:

tabulate country, generate(country)
generate interaction=women*country
xi:mlogit dependent women country1 country2 country3 interaction1
interaction2 interaction3, baseoutcome(0)

margins, dydx(women country1 country2 country3 interaction1 interaction2
interaction3)predict(outcome(1))

Maarten basically just answered this on a different thread. You have to be using factor variable notation instead of computing the interactions separately. Otherwise Stata doesn't know it is an interaction. The code would be something like

mlogit dependent women i.country i.women#i.country

For more, see http://www.nd.edu/~rwilliam/stats/Margins01.pdf

-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW:    http://www.nd.edu/~rwilliam

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index