st: tests in panel data set

[Christopher F Baum <baum@bc.edu>]

Giorgio writes

> Thanks for your answer Kit,
> however, How should I test the autocorrelation within the panel in my 
> panel
> dataset (T=31 and N=143)? Should I use xttest2 just for a subsample?
> thanks Giorgio
Note that xttest2 does not test for autocorrelation; it tests for 
contemporaneous correlation across panel units, which is not at all the 
same thing as testing for autocorrelation within the units of a panel.

Suggest you consider xtregar. If the estimates of \rho generated by 
xtregar are not significantly different from zero, then you do not have 
to worry about AR(1) within the units' timeseries.

Best wishes
Kit

*
*   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/