> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Richard Williams
> Sent: Friday, January 28, 2005 5:18 AM
> To: [email protected]
> Subject: Re: st: Inserting -e(sample)- when using -bootstrap-
>
> At 05:35 AM 1/28/2005 +0000, Clive wrote:
> >All,
> >
> >Hiya! I've tried to run -bootstrap- after the following -corr- run:
> >
> >. corr conch srconch if (srcycle>.25 & srcycle<.5)
> >(obs=60)
> >
> >[...]
> >
> >The -bootstrap- does run, but, as the text says, it runs with _all_
> >observations (305 in total), and not with the 60 in the original -corr-
> >run.
> >
> >Thus is there any way to set up -e(sample)- for -bootstrap- after -corr-
> >or any estimation command which for whatever reason does not set
> >-e(sample)-? Thanks.
>
> I've never used -bootstrap-, but could you first create a data set with
> only the 60 cases you want? e.g.
>
> keep if !missing(conch, srconch) & (srcycle>.25 & srcycle<.5)
>
Dropping missing observations is the recommended strategy, see [R] A-F pages
123-124.
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/
