Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Justina Fischer <JFischer@diw.de> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Antwort: RE: st: Marginal Effect |
| Date | Mon, 10 Jan 2011 16:36:46 +0100 |
.. I guess he wants the formula for converting estimated coefficients into marginal effects.
Justina
-----owner-statalist@hsphsun2.harvard.edu schrieb: -----
An: statalist@hsphsun2.harvard.edu
Von: Maarten buis <maartenbuis@yahoo.co.uk>
Gesendet von: owner-statalist@hsphsun2.harvard.edu
Datum: 10.01.2011 04:02PM
Thema: RE: st: Marginal Effect
--- On Thu, 6/1/11, s_azagba@live.concordia.ca wrote:
> > I estimated a random effect probit model using xtprobit
> > in stata 11.
<snip>
--- On Mon, 10/1/11,<s_azagba@live.concordia.ca> wrote:
> How can l adjust my estimated coefficients by
> sqrt(1-e(rho)) so that the adjusted coefficients can be used
> in my marginal effects
"adjust" can mean a great many operations, what exact
mathematical operation do you want to perform on your
coefficients?
-- Maarten
PS. One alternative direction you may look into is to compute
the integral over the unobserved group-level variable by
simulation using a similar argument that underlies Maximum
Simulated Likelihood, see e.g. the special issue on MSL in the
Stata Journal: <http://www.stata-journal.com/sj6-2.html>. This
is by no means a complete suggestion, it is just an intuition
that one possible solution may be found in that direction.
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://www.maartenbuis.nl
--------------------------
*
* 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/