Dear all
I am running a ordered logit model on a series of X regressors. One of
my regressor (x3) is endogeneous so I was considering a 2SLS.
The Stata command would be:
ivreg2 Y x1 x3 (x3 = z1 z2)
The problem is that Y (the dependent variavel is a ordered variable that
takes values 0, 1, 2, 3,etc.
The endogeneous regressor X3 is a discrete variable that takes values
0,1.
So the first stage would be a logit model, the second stage a ordered
probit model.
-ivprobit- assumes a continous endogenous variable (I think) and ivreg2
is for continuous variables.
Does any one has any suggestions on how to deal with this?
Thanks
Helena Isidro
Cass Business School
United Kingdom
*
* 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/
