--- "Karfakis, Panagiotis (ESAF)" <[email protected]> wrote:
> is there any way I could set a constraint in biprobit so that the
> correlation of the residuals is zero?
In that case you can just estimate separate -probit-s. Alternatively
you can use -constraint-. In that case you need to know that
-biprobit- does not maximizes the likelihood with respect to the
correlation coefficient, but with respect to the Fischer's Z
transformed correlation. However, the Fischer's Z transformed 0 is
still 0, so that is no problem in this case. Below is an example of how
to do all this in Stata.
*------------------ begin example ------------------------
webuse school
biprobit private vote logptax loginc years
constraint 1 [athrho]_cons=0
biprobit private vote logptax loginc years, constraint(1)
probit private logptax loginc years
probit vote logptax loginc years
*------------------- end example -------------------------
(For more on how to use examples I sent to the Statalist, see
http://home.fsw.vu.nl/m.buis/stata/exampleFAQ.html )
Hope this helps,
Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
