I would like to run a Chow test for equality of coefficients across two
Probit models.
A procedure that works in linear models, as previously discussed here, is
the following:
The model is:
y = a1 + b1*x1 + c1*x2 + u for group 1
y = a2 + b2*x1 + c2*x2 + u for group 2
But we can collapse the two equations:
y = a3 + b3*x1 + c3*x2 + a3'*g2 + b3'*g2*x1 + c3'*g2*x2 + u,
where g2=1 if group is 2 and g2=0 otherwise, estimate this and then test
that g2 g2*x1 and g2*x2 are all equal to zero.
Intuitively, this procedure should work in a nonlinear model too, but I
wonder whether this hides some pitfall.
Any hint would be appreciated.
Many thanks
Giulio Zanella
*
* 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/
