What rules do you want to apply for
combining them? Presumably if one variable has a value but the other doesn’t,
then you’d take the one that has a value – and if they both have
the same value, then that’s not an issue. But what if they are both
non-missing and have different values?
From: SPSSX(r)
Discussion [mailto:[hidden email]] On
Behalf Of Janice Ranne
Sent: Thursday, February 26, 2009
4:13 PM
To: [hidden email]
Subject: combineing variables
I am using SPSS Version 16 grad pack. For my
dissertation, survival analysis (Cox regression) is the main analysis technique
I’ve selected.
The data set I am using (Healthy Steps for Young Children
Program Evaluation) abstracted information from medical records.
Problem: The dependent variable I am using was
abstracted twice, without an explanation in the report. Since the
enrollment in the study was rolling, I suspect the people who abstracted the
data just made a second tour through to make sure they got everything. I
don’t want a repeated measures analysis, just a single DV.
Both of the variables are same, categorical, and I’ve
recoded them both as 1 = informal screening; 2 = formal screening.
Sometimes kids got a 1 or 2 (or nothing) in the first variable and maybe 1 or 2
(or nothing) in the second.
When I tried to compute a variable to combine the 2 variables,
I just got an addition. When I tried to combine the variables with an
if..then statement, I got messages (several tries) that something wasn’t
done correctly. I can’t figure out what I have done improperly for
this to work.
Does anyone have an idea that could help me combine these 2
variables into 1?
Many thanks, Janice
Locked
