It seems that the general comments on -predict-
after -xtgee- are an exaggeration in this case,
as no specific option is available that
produces any flavour of residuals.
No matter, you can still use -predict-
to generate predictions and (e.g.) plot those
against observed. Use the GIC: the
graphical investigation criterion. Or
calculate your own residuals from observed
and predicted.
That might tell you more than any other ?IC
purporting to encapsulate all information on
badness of fit in a portmanteau statistic.
This is all supposing that there isn't
some well-known argument showing that
with -xtgee- residuals are a snare,
a delusion and generally poor citizens.
Also, I don't know how much juice there
can be in panels 3 time units long.
Nick
[email protected]
[email protected]
> Please forgive my ignorance if this question is nonsense.
> I'm trying to fit a GEE model to a panel data collected at 3
> points in time. My outcome variable is continuous and I'm
> considering the family of distribution as gamma with log link
> and unstructured correlation structure.
>
> Although the help menu for postestimation for xtgee tells me
> that the predict command can be used to predict residuals,
> stata gives me an error:
>
> .predict r, residuals
> option residuals not allowed
>
> Does stata allow residuals for xtgee?
>
> Also, is there any goodness of fit statistics for xtgee: AIC
> or BIC ?. How would one check whether the model fits the
> data well? (other than comparing the estimated correlation
> matrix to the actual and looking at the predicted values )
>
> I'm using version 8.2
>
> Any comments or suggestions would be appreciated.
>
> Leny
>
>
>
> *
> * 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/
>
*
* 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/