[R] Complex survey analysis help

[Thomas Lumley]

On Sun, 24 Sep 2006, justin bem wrote:

> Hi dear all,
>
> I have a complex survey data to analyse. I have a stratified survey with three
> stages level. The first stage is a PPS, but all other are SRSWOR. The solution 
>propose in survey package is to considere PPS as SRS with repetion.

No, the solution proposed is to consider it as PPS with replacement.

> I have try this
>
> E3stage<-svydesign(ids=~stage1id+stage2id+stage3id, fpc=~fpc1+fpc2+fpc3, ...)
>
> This is the value for WOR sampling at all stage. What value should I give to >fpc1 to have the same value of variance that in sampling with repetion ? I try >fpc1<-rep(0,length(data)) I get a error message.

For sampling with replacement you just omit the fpc and specify the first-stage id and the sampling weights

E3stage <-svydesign(ids=~stageid1, weights=~weights)

       -thomas

Thomas Lumley			Assoc. Professor, Biostatistics
tlumley at u.washington.edu	University of Washington, Seattle