Hi Ash!!
Im not sure if it will help you because I don't know if I understood
well your query. First of all, what do you mean by correlation between
panels? Do you mean autocorrelation of errors? If that is your case,
that is, you want to test for autocorrelation, then you can use the
option xtregar,lbi. The command xtregar assumes theres autocorr of order
1. and the command lbi afterwards will allow you to test the null
hypothesis of no autocorr (it generates a modified version of the Durbin
Watson test for panel data). I don't know if it is of some help, but let
me know as im doing right now the same as you, ie, im running also a
panel data with fixed and random effects.
Dolores (University of York, UK)
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Ash Alankar
Sent: 19 June 2003 15:41
To: [email protected]
Subject: st: Fixed Effects Panel Regression with correlation between
panels
Hi,
I have a panel data set and would like to run a fixed
effect
regression (different constants for each panel)
accounting for
correlation between the error structure of each panel.
It seems that
xtreg, fe does not allow for this. Is xtgls the
appropriate command
to use, i.e. does it implicitly estimate a fixed
effects model? (I am guessing it does not and simply
restricts to constant to be equal for all individuals (panels)). Any
insights would help.
Thanks in advance.
Ash.
__________________________________
Do you Yahoo!?
SBC Yahoo! DSL - Now only $29.95 per month! http://sbc.yahoo.com
*
* 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/
