You need to use analyze>table>custom table. However, the % table and
significant table will be two separate ones. I think there is a way to
merge the two by downloading merge table module from
www.spss.com/devcentral.
suvash
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of
Zhenling Jiang
Sent: Wednesday, November 19, 2008 12:35 PM
To:
[hidden email]
Subject: Sig testing (Comparing column means/proportions)
Hi all,
I'm trying to compare how 3 groups of respondents differ in terms of the
answers they give in a survey. I hope the result could look something
like
this:
Group 1 Group 2 Group 3
A B C
Q1 10% 50%A 30%
Q2 70%B 22% 40%
......
I'm totally making these numbers up, but you get the idea.
I've tried MarketSight, it has a nice-formatted output and sig tested,
the
only problem is when the 3 groups are not mutually exclusive,
MarketSight
won't give me sig testing anymore.
I've also tried SPSS Custom Table, it can do sig testing even when
groups
are not mutually exclusive, but it'll separate the number results and
column numbers indicating sig testing into two tables, and I didn't find
an easy way to put them back together.
How should I approach this? Thanks very much!
Zhenling
=====================
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
=====================
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
