st: how to perform GLS with 3 layers - country year industry?

["calvin ho" <calvinho@hotmail.com>]

Dear stata experts,
I am working on a "3-layer (i, j, k)" panel dataset. In particular, the 
dataset has 3 layers, i= industry, j=year and k=country. it looks like:
ind1 year1 co1
ind1 year2 co1
ind2 year1 co1
ind2 year2 co1
ind1 year1 co2
ind1 year2 co2
ind2 year1 co2
ind2 year2 co2
...
I am using stata7 and want to correct for heteroasticity (within and across 
industry) and serial correlation (within industry AND country). Is there 
anyway I can do using stata. I could not use "xtgls y x1 x2, i(industry) 
t(year) p(c ) c(a )"
since there is only i and j, and j will not be unique within each industry 
(same year with different industries). Please advise.
Many Thanks!
Calvin

_________________________________________________________________
All the action. All the drama. Get NCAA hoops coverage at MSN Sports by 
ESPN. http://msn.espn.go.com/index.html?partnersite=espn

*
*   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/