Dear statalist,
I'm a actually a research fellow at the dept of economics (CIRANO,
Montreal). I've read your very interesting discussion on statalist
(Mon, 9 Jul 2007 09:25:59 -0400) about the hetereoskedasticity and
serial correlation for xtprobit or xttobit. Indeed I and my co-authors
have exactly the same problem as you. We aim at estimating a two step
procedure using a xtprobit mode and then a xttobit. We have been asked
by some referees to cluster our standard errors at the individual?
However this option does not exist on stata 9. Have you any solution
to use robust standard error using xttobit? We have been told that
such cluster option could exist on stata10 but we have not yet update
our stata version. Is there any command on stata 10 for this?
Thanks a lot by advance for your answer.
David
*
* 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/
