Re: st: Sampling without replacement?

[Lucas <lucaselastic@gmail.com>]

Hi,

How did you obtain the 1,000 heads-of-households?  In sampling without
replacement you select household 1 (the Smith household), set it
aside, then select household 2 (the Jones household), and so on.  In
sampling with replacement you select household 1 (the Torvald
household), note that, put it back in the population, then select
household 2 (which could be either the Debian household OR the Torvald
household), and so on.

Which did you do?  That will determine whether you sampled with or
without replacement, not who ends up in the sample.  It is possible to
sample with replacement and still have 1,000 unique households in the
sample of 1,000.

HTH
Sam

On Sat, Jul 27, 2013 at 7:22 AM, Jessica Boatwright <jbhokie1@vt.edu> wrote:
> Hi,
>
> I want to make sure that my assumption that I sampled without
> replacement is correct. I conducted a choice experiment and to collect
> my data I sent out a mail questionnaire. I sampled 1,000
> heads-of-households (i.e. I had 1,000 addresses, all of them unique).
> Each respondent answered 4 choice questions. Is this still considered
> sampling without replacement?
>
> Let me know if you need any additional information to answer my question.
>
> Thank you!
> Sincerely,
> Jessica
> *
> *   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/