Is there a way to test for endogeneity & heteroskedasticity with -xtivreg-?
I have an unbalanced, random effects panel (68 observations, 8 years). I
strongly suspect one variable to be endogenous, but I don't know how to
test for it. I have tried to use the Hausman test as for -ivreg-, but got
the error message:
model fitted on these data fails to meet the asymptotic assumptions of the
Hausman test; see suest for a generalized test
but I am not sure what to do about that given that I have a panel dataset.
Moreover, I don't know how to test for heteroskedasticity with -xtivreg-.
Any suggestions would be much appreciated.
