st: psar1 - is there a way to test?

["Bradley, Steven W" <swb@indiana.edu>]

I am using xtgls and am trying to determine whether psar1 or ar1 best represents my data.  I have a 960 new firms and a T of 9 years.  I could argue from a theoretical standpoint that individual firms from a number of different industries could have different AR1's.
 
xttest1 may test for this but I received an error due to an unbalanced panel.
 
Any recommendations for testing, comparing results that would help me make a decision?
 
Thanks for your help!
 
Steve

*
*   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/