Re: st: time series from panel data

[Cory Smith <corybsmith@gmail.com>]

Don't do the by/egen. Instead,

collapse (mean) eps, by(date)

On Sun, Feb 10, 2013 at 12:36 PM, Whelan, Paul
<paul.whelan07@imperial.ac.uk> wrote:
> Hi,
>
> I would like to take the 'mean' of the residuals from a panel
> regression at each point in time to plot the average residual
> in the cross-section as a time series. Here is an example and
> the code I am using :
>
> xtreg y x1 x2, fe vce(robust)
> predict yhat
> generate eps = y - yhat
> by date, sort: egen mean_residual = mean(eps)
>
> I would then like to export the resulting mean_residual to excel
> as a single time series i.e., one observation for each date. The
> problem is that I get many mean_residuals for each date corresponding
> to each entity in the cross-section at that point in time.
>
> Is there a simple way to extract a single time series?
>
> thanks
>
> *
> *   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/
*
*   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/