Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: autocorrelation


From   "Thushyanthan Baskaran" <tbaskaran@diw.de>
To   statalist@hsphsun2.harvard.edu
Subject   st: autocorrelation
Date   Thu, 28 Apr 2005 13:06:55 +0200

Hi All,

First of all I've to apologize for beeing a novice to STATA :). However,
I already have a question:
I'm trying to estimate a gravity model with panel data. I've used the
xtserial command to check for serial correlation and found that the null
of no serial correlation was rejected. Heteroscedasticity  is present,
too. Now I would like to know if it is possible to control for both. The
xtreg doesn't seem to have some kind of robust option. I know that there
are many other commands that should be capable of handling my problem
(xtgls, prais), however, they all don't work properly, presumably due to
the specific structure of my data: I've got ~ 800000 observation,,
~200000 cross-section units(unbalanced panel)  and  7 time-periods. I
get errors like "too many values" or "matsize should be at least
20000(!) ".  I would be very grateful if someone had a solution! Thanks!


Thushy


*
*   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/



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