Proc Surveyfreq with jack-knife weights for categorical variables

[tipscodesas]

I am using proc surveyfreq with jack-knife replicate weights to describe frequencies across variables in a survey that used address based sampling. Some of the variables are coded by individual selection - for example, a survey question asks respondents to pick three top choices, so the actual dataset made each individual choice a variable with a Yes/No 0/1 response. Which SAS procedure that incorporate jk weights should I use in this case to describe the frequency for the entire question for the three top choices?

[DWilson]

It's not clear to me exactly how your data are structured and how you'd like to summarize your data.

If each individual choice is given a yes/no response, it is not clear how you could determine for a particular respondent, which item they ranked first, which they ranked 2nd, and which they ranked 3rd. Can you determine that from the data?

If you cannot, then you could create separate distributions for each y/n variable so see which item was selected the most (which doesn't mean that that item was ranked at the top the most.)

If you can tell how each person ranked an item, then you could calculate three distributions: 1) Distribution of items that selected as a top choice, 2) Distribution of items that selected as a second choice, 3) Distribution of items selected as a third choice. 

If those summaries don't appeal to you, you should think about what you mean when you say "frequency for the entire question for the top 3 choices."  One combined approach would be to define all possible combinations of the three top choice selections made by respondents and look at the distribution of those combinations. e.g. 3-1-2, 1-5-10 (in order of ranking: choice1 -choice 2 -choice 3).  

In all of these cases, you can use proc surveyfreq.