Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Cecilia Ann <xqcecilia@msn.com> |
| To | STATA List <statalist@hsphsun2.harvard.edu> |
| Subject | st: xthtaylor |
| Date | Wed, 1 Dec 2010 20:21:36 -0500 |
Hi, I use xthtaylor command for panel data model which includes time-invariant variables.It works. When I apply the same code for model without time-invariant variables, stata shows error reminder.But Hausman test gives me a relative large negative value, which implies xthtaylor is a better method.So, I am confused now. What method I should apply for models without time-invariant variables(FE and RE do not work here)? Thanks for help. Ann * * 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/