Dear listers,
this is a rather econometric question.
In a panel setting, the Hausman test provides insight about the correlation of regressors with the individual level random effect. When I compare Random Effects and Fixed Effects Estimators, a low p-value tells me that such a correlation is probably present and hence RE inconsistent.
Now I consider to run a RE tobit estimation on the same model since I have a high proportion of zero observations in the dependent variable. Is this a bad idea when my previous Hausman Test told me that the RE assumption is probably not appropriate?
Best,
John.
_______________________________________________________________________
Jetzt neu! Schützen Sie Ihren PC mit McAfee und WEB.DE. 30 Tage
kostenlos testen. http://www.pc-sicherheit.web.de/startseite/?mc=022220
*
* 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/