[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: ivprobit and overid
The Baum-Schaffer-Stillman team recently released a version of -
overid- (test of overidentifying restrictions) which works after
ivprobit, ivtobit and reg3. The help for use after ivprobit indicates
that 'until official Stata is fixed' you should use the depvar()
option to indicate the dependent variable in your ivprobit. Well,
official Stata was fixed, but not in such a way that our routine
works unless you use the depvar() option. We will issue a fix that
corrects for their fix presently. (The prior version of ivprobit did
not provide e(depvar). The new version does populate e(depvar), but
with multiple variables).
The existing version of overid on SSC will work fine with ivprobit as
long as you specify the depvar() option.
Thanks to Hiroyuki Kawakatsu for bringing this to our attention.
Kit Baum, Boston College Economics
An Introduction to Modern Econometrics Using Stata:
* For searches and help try: