Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: query on xtpcse


From   "Massimiliano Tani Bertuol" <mtani@efs.mq.edu.au>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: query on xtpcse
Date   Thu, 06 May 2010 12:13:16 +1000

Hello statalist
I run a regression on a panel with an I(1) dependent variable, one I(1) regressor, autocorrelation and cross-panel correlation. There iseems to be cointegration between the two I(1) variables. To control for correlation across the panel and the autoregressive error term, I use ordinary panel-GLS specifying the option xtgls...., panels(corr) corr(ar1). 
I understand that in this case the standard errors are too small. Hence I use xtpcse, ...corr(ar1) which, according to the manual, takes into account the cross-panel correlation. 
I understand that the Prais-Winsten estimator assumes that the coefficient of the AR(1) term is common to all industries. Is this the reason for which the command xtpcse controls for cross-industry correlation, or is this taken into account by some other specification? Is there some reference you might suggest about this use of PW estimation (I have only found references about its use to control for autoregressive errors, not to control for cross-panel correlation)? 
Unfortunately I was not able to find an answer reading the manual. 
Thank you in advance for any feedback you might give





*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index