I apologize for not properly explaining what I intend to do. Hopefully
this time I will clear up the confusion.
I have 91 datasets, named 1910 to 2000 in increments of 1. Each dataset
has 1 variable. What I wish to do, is use stata to take a 5 observation
sample from each dataset, without replacement, and then do so 10 times
so that I have 10 random samples of 5 observations from each complete
dataset. Now, I realize that the way I have it set up, Stata would save
the results in 910 different new datasets. This is where things become
more difficult. If possible, I would like the results to be saved in a
single dataset for each original dataset, storing each random sample as
a different variable. So, instead of 910 new datasets, I would have 91
datasets with 10 variables in each dataset, and each variable containing
5 observations.
The code I have now works with respect to creating the samples, it just
needs help on how to save the samples in a more concise form.
forval x =1910/2000 {
local i=1
while `i' <=10 {
use `x'
sample 5, count
save sample`x'`i', replace
local i= `i' +1
}
}
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Nick Cox
Sent: Monday, October 30, 2006 3:59 AM
To: [email protected]
Subject: RE: st: Sample command question
Partly to echo Richard's comment.
One key thing that remains unclear is quite what you mean by
"database", as Stata has no such notion. Is this a Stata
dataset or a bundle of Stata datasets, or is the Stata
processing a means towards an end of holding the data
in some other form?
Similarly, I don't know what "term" means here either.
In broad terms, your specification seems a long way from the code
you posted.
Perhaps you should work on the specific suggestions already
made, as I don't think your problem is yet precise enough
for anyone to write down code without making further wild
guesses.
Nick
[email protected]
David McClintick
> Perhaps I can clear up what it is that I am trying to accomplish.
>
> I have 91 variables. I want to generate 10 random samples of each
> variable. So, for instance, for the first variable I would
> have 10 sets
> of 5 observations, only using observations from that variable. Thus,
> when all is said and done, I should have 10 individual databases, with
> each database containing 91 variables with 5 terms in each one.
>
Richard Williams
> At 09:46 PM 10/29/2006, Nick Cox wrote:
> >Richard's line of code does what you ask.
> >It works on just the variable that you are focusing on.
> >
> >I can see some other problems, some trivial, some
> >not so, that you will face.
>
> Other than the 20 problems Nick points out, it should work fine. :)
>
> One other thing I wondered about - each of the little mini-samples is
> going to include all the variables. Is that what you want, or did
> you just want each sample to include the X in question? You keep on
> referring to "5 terms" rather than "5 cases" which is why I ask this.
>
> Without knowing anything about the Xs, it is hard to tell what the
> purpose of the program is, but I do wonder if maybe there aren't some
> other logical errors lurking out there or if there are better ways of
> approaching it.
*
* 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/
*
* 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/
