1. The fpc values must be constant within sampling strata, not
post-strata. Stata believes that there is just one sampling stratum
(i.e. the whole population) in your design, because you did not set
the strata() option.
2. Finite population corrections are appropriate only for descriptive
analyses. Omit the fpc() option, if you are doing regressions or
hypothesis tests. See references at:
http://www.stata.com/statalist/archive/2009-02/msg00806.html .
-Steve
On Wed, Sep 23, 2009 at 5:16 PM, Peter Muhlberger <[email protected]> wrote:
> Hi folks: Any thoughts on this mysterious error msg?
>
> I get the following error...
>
> . svy: reg motivhlthQ25d knowfewprofsQ26a badexperQ26b
> (running regress on estimation sample)
> fpc for all observations within a stratum must be the same
> r(461);
>
> ...using this syvset command:
>
> svyset School_Number, poststrata(category)
> postweight(categorySchoolsN) singleunit(centered)
> fpc(NumSchoolsInCategory)
>
> When I do a crosstab on category and NumSchoolsInCategory, there is
> only one NumSchoolsInCategory for any given category, thus fpc values
> are identical for all observations in a given stratum--contrary to the
> error message. r(461) might also indicate some issues w/ calculating
> the variance. I have a minimum N of 36 per category & max 294, so I'd
> think variance calculation shouldn't be a problem.
>
> School_Number is an identifier for each school. category is a strata
> identifier (subsets of schools with similar characteristics).
> categorySchoolsN is the number of students in a given category and
> NumSchoolsInCategory is the number of schools in a given category.
> There are 8 categories.
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
--
Steven Samuels
[email protected]
18 Cantine's Island
Saugerties NY 12477
USA
845-246-0774
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
