|From||"Lavie, Dovev" <firstname.lastname@example.org>|
|Subject||st: hausman / suest tests for xtregar|
|Date||Sun, 23 May 2004 15:13:14 -0400|
I am interested in comparing fixed effects and random effects models in xtregar.
My model fails to meet the asymptotic assumptions of the Hausman test, and I cannot use suest since the score option is not available in xtregar.
Does anyone know how to overcome this limitation or can offer alternative tests for deciding whether to use random or fixed effect models?