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 on April 23, and its replacement, statalist.org is already up and running.


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

st: Which estimator to use for correlation among panels?


From   "Klaus Giesler" <BAGZZlash@gmx.de>
To   statalist@hsphsun2.harvard.edu
Subject   st: Which estimator to use for correlation among panels?
Date   Mon, 10 Oct 2011 15:22:25 +0200

Hi everyone,

I got a balanced panel. Its time series dimension spans over t, t = 1, ...,
T, the cross-section spans over i, i = 1, ..., I.
The dependent variable contains the exact same time series in every panel.
Therefore, it does not vary with i, say, it's constant over i.

I suspect that there is autocorrelation within the groups of an explanatory
variable. Here's my (reduced) model:

y_it = b0 + b1 * x_it + u_it,

where y_it = y_jt for all i, j. Then, I suspect cor(x_it, x_jt) != 0 for at
least some i, j. My question is: What estimator do I use in Stata for that?
I need an estimator that controls for this possibly present correlation but
still returns "interpretable" coefficients. I played around with xtpcse,
xtdpdsys and xtdpd, but I'm not sure if they are really suited for my
purpose. Is there anyone that could point this out for me?

Best

Klaus
-- 
NEU: FreePhone - 0ct/min Handyspartarif mit Geld-zurück-Garantie!		
Jetzt informieren: http://www.gmx.net/de/go/freephone
*
*   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