How I use t-test in complex survey deign

[dode]

Hello everyone,

How I use t-test in complex survey deign, I read I can do that through surveymeans, but I still don't know how, please help me with the code

Thanks

[ballardw]

Add T to the proc surveymeans statement to request a t-test.

The Ratio statement would be used to indicate which variables to test.

Ratio x y / z t ; where x y z and t are variables will request tests for x with z, x with t, y with z and y with t.

If a variable appears on both sides to the / then the test of a variable with itself is ignored.

[dode]

Hello ballardw ,

Thank you so much for replay, I provided you the code below, I added T, please can you see if i did the code correctly.

proc surveymeans data=transform;
var cognitive_impairment /T;
domain education;
cluster raehsamp;
strata raestrat;
weight r7wtresp;
run;

[dode]

proc surveymeans data=transform; T;
var cognitive_impairment ;
domain education;

ratio cognitive_impairment/education;
cluster raehsamp;
strata raestrat;
weight r7wtresp;
run;

can you please check if the code is correct

thanks

[dode]

also how I di ANOVA in survey complex design ?

and Wilcoxon?

[SAS_Rob]

You can use Proc SURVEYREG to fit an ANOVA to complex survey data.

There are no procedures to fit non-parametric models, although I suppose you could apply SURVEYREG to the ranks.  You would have to do a little research to see how this would be different from the SRS-world but it might be a possibility.  I believe this book even discusses it although I don't recall where exactly in the book it is.