Programming the statistical procedures from SAS

multivariate method on complex data

Occasional Contributor
Posts: 15

multivariate method on complex data

Hi all,

Can anyone help me with a question on using complex data?

I know that we need to use strata and cluster statement in order to use weighted data. But I could not find any example that these statement could be used in manova...

If I write my model like this, it will run. But I can only have one dependent variable. 


proc surveyreg data = wave1.cro_section_neededIV;
cluster psuscid;
strata region;
weight gswgt1;
class BIO_SEX;
model nonagressivedelin =BIO_SEX parentattchemnt schoolattachment delinqpeerw1
age eduw1/ solution ;



If I add " manova h= _ALL_ ;" after model statement, it will not run...

So it means when using weighted data, there is no way to use multivariate method? I also tried to use proc glm, not working with strata statement, either. Only proc reg is allowed to go with "survey" and strata statement. WHY?

Super User
Posts: 13,523

Re: multivariate method on complex data

Did you try a simple ANOVA option on the model statement?


None of the documentation I have seen for SURVEYREG has MANOVA as an option. So I would expect an error.


When you run code and get errors it might help the forum answer you questions if you show the log in a code box opened with the forum {I} menu icon to preserve the formatting of messages.

Occasional Contributor
Posts: 15

Re: multivariate method on complex data

Thank you for your reply! I tried univariate (anova) and it worked. But I can't help wondering people like me who use complex data would face a dilemma: if we have two DVs, and they are correlated. We wanted to use multivariate regression. However, in SAS, it seems we could not...right? 

Then how about poisson, logistic regression? Maybe survey statement also do not go together with them, either. I only know survey statement could go with proc reg, and proc phreg. 

Super User
Posts: 13,523

Re: multivariate method on complex data

Surveylogistic for complex data and logistic regression.


Sometimes when you get into the complex samples the appropriate approach for some traditional statistics tests are not as well defined.

Ask a Question
Discussion stats
  • 3 replies
  • 1 like
  • 2 in conversation