Oh yes, of course. You are right. Thank you.
On Mon, Oct 5, 2009 at 12:02 PM, Nick Cox <[email protected]> wrote:
> Apologies for previous premature post.
>
> My guess:
>
> Second time round the loop, your data start out sorted -id difa1-. But
> you then ask to do things -by id treated:-. Those two aren't consistent.
>
>
> The first line in your loop should perhaps be
>
> bysort id treated : ...
>
> Nick
> [email protected]
>
> Dorothy Bridges
>
> Stata stops the following loop with a "not sorted" line after the
> "sort id difa`i'" command (not after the subsequent command, after the
> sort command). What am I missing? Thanks!!
>
> forvalues i = 1/5 {
> by id treated: gen var_a`i'=.
> replace var_a`i'=ln_var if ante_`i'==1
> by id treated: egen var_a`i'_mean=mean(var_a`i')
> gen difa`i'=.
> replace difa`i'=var_a`i'_mean - var_a`i'_mean[_n-1] if id==id[_n-1]
> replace difa`i'=. if difa`i'==0
> sort id difa`i'
> replace difa`i'=difa`i'[_n-1] if difa`i'==. & id==id[_n-1]
> }
>
> *
> * 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/