Nils, this is a question probably best addressed to the SPSS listserv (assuming your link below provides all the specifics). Hence my cc'ing the list and hopefully you might receive an answer. I have never used multiple response for testing so I cannot help you. I just used the multiple comparisons test for independent groups (i.e. 3 or more) in a contingency table. SPSS relies on a Bonferroni adjustment - if you request it. Good luck - Dominic
*********************************************
Dominic Lusinchi
Far West Research Consulting
Applied Statistics – Social Research – Sociology
San Francisco, California
[hidden email]
1-415-664-3032
CV:
http://www.farwestresearch.com/staff/dl/dlcv.html*********************************************
-----Original Message-----
From: Survey Research Methods Section of the ASA [mailto:
[hidden email]] On Behalf Of Nils Glueck
Sent: Tuesday, July 28, 2015 12:29 PM
To:
[hidden email]
Subject: SPSS: z-tesing for multiple response sets
Dear list members,
this one is for all people who are conversant with SPSS and survey data. Please take a look, I would be very pleased about any kind of opinions or hints.
Currently I am trying to find out how "SPSS multiple response sets" are treated by SPSS. The scenario (proportions testing / z-testing in "custom tables") seems oddly specific, still I came to the point where the SPSS logic seems like a blackbox to me, and I cannot precisely tell what the software is doing - which makes me nervous.
The whole thing might be easy, so please do not feel overwhelmed by this StackOverflow post (the datasets are both simple and included in the post):
http://stackoverflow.com/questions/31673171/custom-tables-how-does-spss-treat-multi-response-sets-differently-from-categori/
The pros and cons of SPSS usage have been debated all over; still it would be a very important step for me to get closer to the solution. Am I doing it all wrong?
Thank you so much for answers. :)
Best regards,
Nils Glueck (M.Sc. Market Research)
E-Mail:
[hidden email]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
To subscribe/unsubscribe SRMSNet:
http://listserv.umd.edu/cgi-bin/wa?A0=srmsnet&D=0&F=&H=0&O=T&S=&T=1SRMS website:
http://www.amstat.org/sections/srms/~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
