Date: Tue, 7 Apr 1998 12:25:49 -0400
Reply-To: Jeff Mather <Jmather@HARTHOSP.ORG>
Sender: "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From: Jeff Mather <Jmather@HARTHOSP.ORG>
Subject: confidence intervals for kappa
Content-Type: text/plain
Hello,
I've been given a dataset from a survey with questions that have multiple
responses in this format:
q3a q3b q3c q3d --(variable name)
1 1 2 2
2 2 2 2 --- 1=yes, 2=no
1 2 2 1
etc
In this example, question 3 can have four responses, identified as q3a -
q3d. Somehow I need to combine the responses so that I can identify
how many reponders reported multiple yes responses and to identify
where the yes came from (ie in case 1, q3a and q3b were yes).
I know the best way to do this is with dummy variables for all the possible
combination of responses to question 3 (with 1 column of respomnses per
question), but they don't have time to do this. Can anyone tell me a quick
way I can get SPSS to give me the info I need with the data set up as is?
Any help would be greatly appreciated
Thank you
Jeff Mather
|