st: var decomposition issues

[Alban Pinz <albanpinz@hotmail.com>]

> Hi guys,
>
> I'm running univariate VARs for each cross-sectional unit in a panel
> dataset ie. [by x, sort : var x, lags(1/2)]. I then want to get
> predicted and residual variables for each regression, however I think
> whats happening is the program is taking the values from the very last
> regression and using them to predict values for the whole sample,
> which is screwing up my analysis of variance.
>
> How can I make stata use the estimates from each individual country
> VAR to give me a predicted value for ONLY that country? Preferably
> some way thats not going to take hours and hours to do. I have no idea
> about programming but I dont think it would be too hard, any help
> would be much appreciated!
>
> Many thanks!
*
*   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/