Thank you Nick. After these commands, mysplit variable has been generated which seems a dummy variable. Mysplit is equal to 1 if the median value of weight is above the p50. Is that right?
Kind regards
Ebru
----------------------------------------
> Date: Thu, 20 Dec 2012 17:12:28 +0000
> Subject: Re: st: split a sample
> From: njcoxstata@gmail.com
> To: statalist@hsphsun2.harvard.edu
>
> sysuse auto
> su weight, detail
> gen byte mysplit = cond(missing(weight), ., (weight >= r(p50)))
>
> Nick
>
> On Thu, Dec 20, 2012 at 4:56 PM, Ebru Ozturk <ebru_0512@hotmail.com> wrote:
>
> > How do we split a sample according to a certain variable? I want to split the sample by using median value of a certain independent variable. Which command should I use?
> *
> * 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/
