[DDI-users] How to code repeated elements?

Richard C. Rockwell richard at ropercenter.uconn.edu
Fri Feb 13 12:47:59 EST 2004


This exchange is interesting as an instance of a larger problem that I 
suspect we have not yet fully dealt with in DDI deliberations.  What Graham 
has is what used to be coded as multi-punched data, in the days when 
computers were powered by steam.  That format was immensely appropriate for 
questions that could have multiple responses.  To be sure, it caused great 
headaches when processing moved from card sorters to computers.

But the concept of questions/variables with validly multiple responses 
persists.  It can occur for opinion data (e.g., "What are the three Most 
Important Problems that the country faces?") and for many other kinds of 
data (e.g., "Please tell me whether or not you are a member of each of the 
following organizations.).  Does the varGrp/grid approach address all of 
the issues that such questions/variables will raise, while retaining the 
conceptual unity of the measurement as a single variable?  Is binary coding 
of each possible response the optimal strategy?

At 09:58 AM 2/13/2004 -0700, you wrote:
>I think you have to repeat everything.  But you should put all your vars in
>a varGrp of type "grid".
>
>-----Original Message-----
>From: ddi-users-bounces at icpsr.umich.edu
>[mailto:ddi-users-bounces at icpsr.umich.edu] On Behalf Of Graham Stark
>Sent: Friday, February 13, 2004 8:12 AM
>To: ddi-users at icpsr.umich.edu
>Subject: [DDI-users] How to code repeated elements?
>
>Hi,
>       could someone give me some guidance?
>
>I'm trying to work out how to code a repeated set of questions like:
>
>"I am going to read out some words and phrases that have been used about
>the political parties. Regardless of which party you would vote for, please
>say in each case whether you think the word or phrase is true or not true
>of  Party A/Party B/Party C
>
>i)    Understands the problems ordinary people face in today's world
>ii)   Shares my values
>iii)  Is honest and principled
>[ etc ]
>
>What's the DDI idiom for this? It seems to me that some combination of
>vargrps and moving the qstn elements outside the variables should do it,
>but it's not clear to me exactly what I should be writing. Can anyone point
>me to an example? Or is it simpler to just write vars that repeat
>everything?
>
>thanks,
>
>Graham
>
>
>_______________________________________________
>DDI-users mailing list
>DDI-users at icpsr.umich.edu
>http://www.icpsr.umich.edu/mailman/listinfo/ddi-users
>
>
>_______________________________________________
>DDI-users mailing list
>DDI-users at icpsr.umich.edu
>http://www.icpsr.umich.edu/mailman/listinfo/ddi-users

--------------------------------------
Richard C. ROCKWELL
Executive Director, The Roper Center &
Institute for Social Inquiry
Professor of Sociology
University of Connecticut
341 Mansfield Road, U-164
Storrs, CT 06269-1164  USA
V +1 860 486-4440
F +1 860 486-6308
Richard.Rockwell at uconn.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lion.icpsr.umich.edu/pipermail/ddi-users/attachments/20040213/e9a60c4b/attachment.htm


More information about the DDI-users mailing list