<>
Fiona said
I have a model of the following form:
y = a + b1x1 + b2x2 + ... +xn + u
Where y = a binary dependent variable (a probit model)
X1 is a binary variable with potential reverse causality (endogenous)
x2 - xn are exogenous variables.
I wondered whether you may use IV for this? and how I would go about
this?
She should look into whether -cmp- (findit cmp) can be used in this
setting.
Kit Baum | Boston College Economics & DIW Berlin | http://ideas.repec.org/e/pba1.html
An Introduction to Stata Programming
| http://www.stata-press.com/books/isp.html
An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html
*
* 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/
