[R] Understanding survey design (svydesign)

[Thomas Lumley]

If you have zeros in the supplied sample weights, the display in the
summary() function will look like this. Nothing is actually wrong with
the calculations, though.

If the zero weights are because of restriction to a subpopulation, you
will get better-looking summaries if you put the whole design into
svydesign() and then use subset() to restrict to the subpopulation.
That way R knows what's going on. It won't affect the answers, though.


   -thomas

On Fri, Jun 6, 2014 at 8:13 AM, Ryan de Vera <ryan.devera.03 at gmail.com> wrote:
> Hi all,
>
>
> I am trying to understand the output of the svydesign function. My question
> is, is there documentation on how the probabilities are computer? Or could
> someone please explain to me how they are? I have this
>
>
> d<-svydesign(id=~PSU, strata=~STRATUM,weights=~w, data=s, nest=TRUE)
>
>
> And this output with summary(d)
>
>
> Stratified 1 - level Cluster Sampling design (with replacement)
>
> With (783) clusters.
>
> svydesign(id = ~PSU, strata = ~STRATUM, weights = ~Sample_Weight,
>
>     data = subset25k, nest = TRUE)
>
> Probabilities:
>
>    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.
>
>       0       0       0     Inf       0     Inf
>
>
> I have read the documentation about the code but it doesn't actually say
> anything about the probabilities. Thank you in advance.
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.



-- 
Thomas Lumley
Professor of Biostatistics
University of Auckland