Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Nick Cox <njcoxstata@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: Fixed effects vector decomposition |
| Date | Mon, 1 Oct 2012 09:28:22 +0100 |
See http://davegiles.blogspot.co.uk/2012/06/fixed-effects-vector-decomposition.html and its references before proceeding any further. Nick On Mon, Oct 1, 2012 at 8:39 AM, fernando luiz mistura <f_mistura@hotmail.com> wrote: > > I am testing the effect of a rarely-changing variable (FDI restrictions) lon the level of FDI stocks. > Under OLS, Random Effects, the effect is significant. However, with Fixed effects it is not. Hausman test tells me that Fixed Effects would be more appropriate. But isn't Fixed Effects unlikely to be adaptable to variable that change slowly overtime or not change at all for some countries in the panel. > Wityh Fixed Effects Vector Decomposition, I significant coefficients but they are much higher than with OLS RE or FE. Is this normal? * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/