----- Original Message -----
From: "karoline mortensen" <[email protected]>
To: <[email protected]>
Sent: Thursday, May 22, 2003 10:12 AM
Subject: st: Swor and sample commands
> Hi,
>
> I would like to randomly select (without replacement) 5% of my data, and
> keep all the data that were not selected. I believe this rules out the
> Stata "sample" command, because that discards the 95% of observations that
> were not selected.
>
> In other analyses I have used the very useful "swor" command (which allows
> the option of keeping non-selected observations). However, now I want to
> randomly select 5% (not an absolute count) of my observations, by an ID
> variable, so 5% of each ID get selected. Swor seems to only allow an
> absolute count to be selected. Is there another option that allows me to
> randomly sample a certain percentage, while keeping all the observations
> in the dataset?
>
> Thanks in advance,
> -Karoline Mortensen
>
You could use -sample2- (findit sample2 will bring up the file)
sample2 5, keep(varname)
Scott
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
