Dear Statalisters,
I've been trying to estimate the following simultaneous probit models:
(1) Y1=a*Y2 + b*X1 + e1;
(2) Y2=c*Y1 + d*X2 + e2.
where Y1 and Y2 are two endogenous binary variables; X1, and X2 are two sets
of exogenous variables of Y1 and Y2 respectively; e1 and e2 error terms.
That is to say, Y1 and Y2 suspected to be endogenously determined by each
other.
I am thinking of implementing the two-stage method discussed in Maddala
(1983) P246-247 (Model 6. y1 and y2 both binary); but am having problems
calculating the adjusted standard errors of the second-stage models.
I understand there's a procedure 'cdsimeq' by Keshk that implements
Maddala's approach when one dependent variable is binary, but the other one
CONTINUOUS. Could someone kindly point out whether there is also a similar
Stata/user-written programme that deals with the case of two binary
variables?
I've searched through the Statalist archive, but couldn't find any relevant
postings.
Your kind help will be greatly appreciated!
Best wishes,
Cher
Q. Cher Li
Department of Economics
Adam Smith Building
University of Glasgow
Glasgow G12 8RT, UK
Tel: +44 (0)141 330 2220
Fax: +44 (0)141 330 1880
Email: [email protected]
Web: http://www.gla.ac.uk/departments/economics/
*
* 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/
