Dear statalisters,
I follow exactly the suggestion of Vince Wiggins to FAQ: Testing for
panel-level heteroskedasticity and autocorrelation (see please
http://www.stata.com/support/faqs/stat/panel.html ) to test, not to sound
strange, for heteroskedasticity after running a xtgls, and I type
.estimates store hetero
.local df=e(N_g)-1
.lrtest hetero . , df(`df')
I get a scaring error message saying
models hetero specified more than once!
No, it appears you have left out the step of estimating the model without
heteroskedasticity. Check the FAQ again. As things now stand, hetero is
being tested against itself.
