Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: Autocorrelation in panel data: xtregar or cluster() option ?


From   Simon Pickert <[email protected]>
To   [email protected]
Subject   st: Autocorrelation in panel data: xtregar or cluster() option ?
Date   Sun, 1 Dec 2013 22:53:12 +0100

Hi Statalisters,

I am looking for advice on how to account for auto-correlation in my unbalanced panel data set on which I want to run a fixed-effects regression. So far, I understand that there are two main possibilities:

xtreg with the cluster() option
or
xtregar


I have an unbalanced panel data set with 40K observations spread across 495 groups. 
Min observations per group = 19
Max observations per group = 209
Avg observations per group = 82

How can I decide which method to use? The results are quite different in my case. 

I found an interesting slide deck from Austin Nichols and Mark Schaffer. http://repec.org/usug2007/crse.pdf 
It seems that the cluster() option performs best.


Thank you for your advice.
Simon
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index