Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: estout, OLS and multiple Heckman selection models


From   "Ben Jann" <ben.jann@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: estout, OLS and multiple Heckman selection models
Date   Wed, 21 Nov 2007 15:51:30 +0100

Can you show an example of what exacly you want (i.e. sketch a table
that looks like the table you have in mind; and maybe give the command
sequence that produces the models)?

It is not completely clear to me how the table should look like, but I
think the solution lies in storing models multiple times and then
tabulate different parts from the copies.
ben

On Nov 21, 2007 3:19 AM, Dimitriy V. Masterov <dvmaster@umich.edu> wrote:
> I am trying to compare estimates from an OLS specification and from
> two versions of the Heckman selection model (one estimated by the
> 2-step and one by MLE). I would like to get put all these in a table
> where I have OLS coefficients in the first column, the selection
> equation in the second, and the two outcome equations in the third and
> fourth. I would like to have the lambdas appear in the third and
> fourth column as if they were coefficients, and to have rho and sigma
> appear at the bottom of the fourth column with standard errors. I am
> having trouble doing this to work with estout since Stata treats
> lambda as a separate equation, and gives it its own column. I've tried
> mucking around with the keep, unstack and equation() options, but I
> can't get exactly what I want. Has anyone gotten this to work?
>
> Dimitriy
>
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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