Hi,
I am working with a long narrow panel (fixed effects) and had to
remove serially correlated errors with xtregar.
Now, there remain two questions after having read the
xtregar chapter in Stata manual xt:
(1) I wonder what procedure Stata actually implements.
After having read chapter xtregar in stata manual xt,
there remain two possibilities:
(a) stata estimates roh, stata does a Cochrane-Orcutt
transformation of each panel, stata then removes the within
panel means and adds back the overall mean for each variable
and estimates the coefficients using OLS on the transformed
data
or (b) stata estimates roh, then stata uses the Baltagi and
Wu (1999) transformation and after that stata transforms
the data that comes out of the B+W(1999) transformation.
OLS is then run on this transformation
(2) Is there a possibility to obtain the Bhargava et al.
DW of the xtregar estimation (after the xtregar procedure
has been applied)?
Thanks a lot!
gerhard
*
* 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/
