I don't think that you can use the -bs- command in your situation for many
reasons. Most importantly, -bs- would not be taking into account the design
features of the survey. This question of whether the svy commands can be
bootstrapped has come up on statalist several times and I don't think its
ever been finally resolved. I would love it if someone would correct me if
I'm wrong on this.
There is a general solution, however, for you to get bootstrapped estimates
from survey data without actually having the pweight/PSU/strata information
made public. You have to get the data administrator to create bootstrap
weights and a set of analysis syntax files. This is exactly what Statistics
Canada is doing with large surveys now. In the past, they had coefficient of
variation look-up tables, which were tedious and rather approximate. Now,
they provide these bootstrap weights. Unfortunately, the syntax files are
huge and complicated and probably require some serious insight into the
original data file (which is why the data administator has to create the
files; I doubt that you could roll your own). The only down-side is that
Stats Can is only providing the syntax files for SPSS and SAS.
Anyway, the process of creating these bootstrap weights and syntax files is
well-documented. You could contact Yves Beland at Stats Canada if you want
to know more about the method.
Best,
Lee
Lee Sieswerda, Epidemiologist
Thunder Bay District Health Unit
999 Balmoral Street
Thunder Bay, Ontario
Canada P7B 6E7
Tel: +1 (807) 625-5957
Fax: +1 (807) 623-2369
[email protected]
www.tbdhu.com
> -----Original Message-----
> From: Michael R. Smith [SMTP:[email protected]]
> Sent: Monday, August 26, 2002 11:47 AM
> To: [email protected]
> Subject: st: Bootstrap and percentages
>
> I'm processing some data that was generated with a complex sample design
> but
> to which, for reasons of confidentiality, I don't have direct access. This
> means that the svy commands are not a practical option. Use of them
> requires
> correction for PSUs with only one case - but the PSUs with missing values
> that reduce them to one case will vary depending on variables in the
> analysis. Submitting my code to the person who runs it in order to find
> out
> when and where to merge PSUs would, then, become an extremely cumbersome
> process.
>
> So bootstrapping looks like the most practical method for inferential
> purposes. It's clear how to do that with regression and related
> procedures.
> But's it's not obvious to me how one should go about using the bs command
> to
> generate standard errors for a percentage table. The bs command requires
> specifying each coefficient to be bootstrapped. How does one specify cells
> in a percentage table? Part of the analysis requires generating percentage
> tables with quite large numbers of cells, so I need to generate a large
> number of standard errors.
>
> I've read what seem to be the relevant sections of the manual and rooted
> around in the FAQs and other documentation for an answer, so far with no
> success.
>
> Michael Smith
>
>
> *
> * 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/
