st: Re:fitting a var...

[Kit Baum <baum@bc.edu>]

She was correctly told that -var- does not work with panels. But VARs 
are merely autoregressions of a set of y variables on a set of lags of 
each of those variables. They can be efficiently estimated by OLS. 
Therefore, since it is a dynamic panel data setting, she can run 
xtabond2 (which I would recommend over official xtabond) for each 
country/firm/etc. in the panel. xtabond2 is capable of estimating 
simpler models than the Arellano-Bond, including anything one can 
specify as OLS or IV.

Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html

On Feb 5, 2005, at 2:33 AM, Agnieszka wrote:


> I would like to fit a var to the pooled data.
> I polled the data and I tried to fit the simple var command to it.
> I have 3 variables and 2 lags for each.
> I get the following message: repeated time values in sample.
>
> Any idea why?
>
> Regards
>
> Agnieszka
*
*   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/