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]

st: gllamm and geqs


From   Jonas Krüger <[email protected]>
To   [email protected]
Subject   st: gllamm and geqs
Date   Wed, 20 Nov 2013 17:37:13 +0100

Hi everyone,

I have a specific question about the gllamm program for discrete
choice models with random coefficient.
My model is based on the random utility equation and a household can
choose between different alternatives.

Utility depend therefore on income, leisure time of male and female
and household characteristics.

My question is about the geqs option of gllamm. I want to estimate a
random slope for the income preference.

E.g.

eq f1: age_m age_f education_m education_f
eq y: y
gllamm alt y ysq lm ylm ylf lf lmlf, i(id) expand(Hc choice o)
link(mlogit) nrf(1) eqs(y) geqs(f1) ip(g) nip(15) trace adapt nocons

As far es I understood it f1 defines the stage 2 equation for the
random coefficient y. But is this the same as a reduced form model,
such as I would include age_m*y etc into the stage 1 equation and they
do not vary across household? Or are they only a specific regression
to determine the random slope of y?

Thanks in advance
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


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