Hello statalisters,
after implementing CDSIMEQ procedure and instrumenting each of the 2 dependent
variables, i have concern over endogeneity of yet another continuous variable
in the second-stage probit equation.
the usual procedure to test for endogeneity in single probit, as per Rivers &
Vuong (1988) is to estimate the reduced form of suspect endogenous continuous
variable (ensuring sufficient identification restrictions,order & rank) and
include the resultant error, along with actual value into the probit. "the
usual probit t statistic on this error is a valid test of the null hypothesis
that the variable in question is exogenous", p474 Wooldridge
can i still implement this in a 2-stage least squares probit ? my concern is
over correct variances.
thanks
claire
*
* 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/