st: Re: statalist-digest V4 #2506

[evan roberts <eroberts@hist.umn.edu>]

David McClintick asked how he could make ten samples of 5 observations 
from 91 different datasets, and end up with 91 different datasets 
combining the samples, with ten variables and five observations.

There is perhaps more efficient code than the following but this seems 
to do the job.  The key thing to do in each sample is to rename the 
single variable to variable`i' (i=1..10), then generate an id variable 
(=_n), merge by id into one dataset and then erase the non-merged 
samples. Your workspace at the end of this procedure has 182 files, the 
original 1910-2000 files with one variable, and 91 other files sample`x' 
with 10 variables sequentially named variables representing a sample.

----
set more off

forval x =1910/2000 {
forval i =1/10 {
	use `x', clear
	sample 5, count
* 	rename x x`i'   * this is the variable you are sampling

	gen id=_n
	sort id
	save sample`x'`i', replace
}

forval i =2/10 {
	use sample`x'1
	sort id
	merge id using sample`x'`i'
	erase sample`x'`i'.dta
	drop _merge
	save sample`x'1, replace
}

use sample`x'1, clear
drop id
save sample`x', replace
erase sample`x'1.dta

}

set more on
-----
Evan Roberts
Minnesota Population Center


> - -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of David
> McClintick
> Sent: Tuesday, October 31, 2006 1:31 AM
> To: statalist@hsphsun2.harvard.edu
> Subject: RE: st: Sample command question
>
> After looking at that code, I realize that I have not been clear enough.
> What I meant by "without replacement" was that I wanted each of the 10
> samples of each dataset to be taken from the original dataset, meaning
> that while no observation could be repeated within the sample, it could
> conceivably be repeated across samples. With your suggestion, it returns
> varying numbers of observations, which I believe is caused by the
> aforementioned issue. Additionally, it seems to return all of the sample
> observations in the first variable?
*
*   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/