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: Simultaneous Ordered Probit and Linear Equation Model, Unbalanced Data, ML Programming


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Simultaneous Ordered Probit and Linear Equation Model, Unbalanced Data, ML Programming
Date   Wed, 21 Sep 2011 10:27:59 -0500

Maarten went into a heroic effort of looking through your code, but I
would suggest using -gllamm- or -cmp- to run this model. You would be
able to run the model with the y* in the elasticity specification that
way.

You would also need to think about Heckman-type version of the model
with inverse Mills' ratio if you have selection based on y1.

On Wed, Sep 21, 2011 at 8:54 AM, Hendrik M <hendrik.m@hotmail.be> wrote:
> Dear all,
>
> I try to estimate an ordered probit model and a linear equation simultaneously with unbalanced data, but I face some problems.
> I use Stata 11.1
>
> The model:
>
> 1. Latent variable model (ordered probit)
> y1 = x1 + beta1*x2 + err1
>
> y1 = {0,1,2,3}
> coefficient of x1 is constraint to 1.
>
> 2. Linear equation model
>
> 2.a. Constant elasticity specification
> y2 = gamma1*x2 + gamma2*ln(y1) + err2
>
> or
>
> 2.b. Fixed Effects specification
> y2 = gamma1*x2 + gamma2*d(y1=1) + gamma3*d(y1=2) + gamma4(y1=3) + err2
>

-- 
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   |   Site index