Re: st: Purging a dataset

[Philipp Rehm <philipp.rehm@gmx.de>]

.
You can use e(sample), which is left behind after the regression (you 
can type "ereturn list" for details).

Example:
sysuse auto, clear
reg trunk rep78
gen sample=e(sample)
pwcorr price trunk if sample

HTH,
Philipp

On 3/28/2010 4:27 PM, Claude Francoeur wrote:
> Hello,
>
> Does Stata provide a command to create a dataset with the observations
> that are used in a regression? For instance, my original dataset
> contains 1,324 observations. Some of these observations contain empty
> variables that are dropped by Stata when doing a regression (N= 1,264).
> I would like to use the tabultae and corr commands on that subgroup
> without having to delete the missing observations from my data file.
>
> Thanks for you help
>
> Claude
>
>
>
>
> *
> * 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/
*
*   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/