In SAS, what is the simplest way to carry out a chi-square test for
independence that accounts for the clustering of observations n a
multistage sample.

Just as PROC SURVEYREG is a survey-design counterpart to PROC REG, the
procedure I have in mind would be a survey-design counterpart to PROC
FREQ.

On Nov 2, 5:52=A0pm, Paul <paulvonhip...@yahoo.com> wrote:
> In SAS, what is the simplest way to carry out a chi-square test for
> independence that accounts for the clustering of observations n a
> multistage sample.
>
> Just as PROC SURVEYREG is a survey-design counterpart to PROC REG, the
> procedure I have in mind would be a survey-design counterpart to PROC
> FREQ.

PROC SURVEYFREQ.

From the documentation:

PROC SURVEYFREQ computes variance estimates based on the sample design
used to obtain the survey data. The design can be a complex multistage
survey design with stratification, clustering, and unequal weighting.
PROC SURVEYFREQ provides a choice of variance estimation methods,
which include Taylor series linearization, balanced repeated
replication (BRR), and the jackknife.

Steve Denham