Also, as a data provider, you would need to perform all the tweaks
like post-stratification and non-response adjustments with each set of
the replicate weights.
My small collection of links on inference through survey resampling is
available at http://www.citeulike.org/user/ctacmo/tag/survey_resampling.
There's more stuff out there, of course.
On Sun, Apr 27, 2008 at 7:54 PM, Melanie Black <[email protected]> wrote:
>
>
> Hi,
>
> I'm looking into using the 'svy' commands and am seeking some advice on
> their use on survey data when the design information is not known.
>
> Say the survey was a stratified, multi-stage design, but the data does not
> contain information on the stratification or clustering, but does include
> weights and (jackknife) replicate weights. Can svy still be used, and would
> it be statistically valid to do so?
>
> Thanks in advance for any help.
>
> Cheers,
>
> Melanie Black
>
> Data Access and Confidentiality Methodology Unit
> Australian Bureau of Statistics
> ph. +61 (02) 6252 7241
>
>
>
> ------------------------------------------------------------------------------------------------
>
> Free publications and statistics available on www.abs.gov.au
--
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: Please do not reply to my Gmail address as I don't check
it regularly.
*
* 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/
