Re: st: Marginal effects after biprobit

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Mon, 1/11/10, momo wrote:
> I run a biprobit regression and all variables are
> significant but I found that the sign of the
> independent variables changes sometimes when I do
> the different combinations for the marginal
> effects after biprobit regression, i.e. (p11),
> (p10), (p01) and (p00). So could this be a problem
> or what. 

It is no problem that the numbers (including the sign)
changes when you ask for different marginal effects. 
This basically means that the answers change when you
ask different questions, which is exactly as it should
be. However, it is a huge problem if you do not know 
which marginal effect answers your question. 

Hope this helps,
Maarten

--------------------------
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/