Dear Stata-listers,
Many thanks to Brian Poi who helped me solve an earlier problem I had using
the user-written program condivreg to compute confidence intervals that are
robust to weak instruments (for more information, see the literature cited
in the help file). I had interacted two variables to create my instrumental
variables, and that created a multicollinearity problem in the first stage.
Instead, I entered the interacted terms manually and there is no problem
anymore.
One more question: Conditional likelihood ratios (CLR) as calculated in
condivreg are robust to non-normal errors, but are they also robust to
heteroskedasticity?
Thanks a lot,
Thi Minh
*
* 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/
