Statalist


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

Re: st: Fw: gllamm for simultaneous equation model with panel data


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Fw: gllamm for simultaneous equation model with panel data
Date   Fri, 6 Feb 2009 22:29:44 -0600

On 2/5/09, Sarai Sapulete <sapuletesarai@yahoo.com> wrote:
>  I am trying to estimate a simultaneous equation model with a dichotomous and a continuous dependent variable, using panel data.
>  I want to estimate the following equations:
>  Y1dichotomous = Y2continuous + X1+X2
>  Y2continuous = Y1dichotomous +X1+X3
>
> The replies to
>  earlier questions of this kind suggest using gllamm, but I cannot find
>  in what way gllamm can be used for this kind of problem.

-gllamm- only works with random effects, and few econometricians are
happy about it. If you are, you need to think carefully about where do
you think the random effects in your model should go. I'd say that
estimating your model with -gllamm- only makes sense if you have panel
data; you can try to twist its hands to work with simple
cross-section, but I suspect you would have to restrict some
variances, and -gllamm- does not like that, for some reason.

-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.
*
*   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   |   What's new   |   Site index