LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (January 2008)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Wed, 9 Jan 2008 14:45:06 -0700
Reply-To:     ViAnn Beadle <vab88011@gmail.com>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         ViAnn Beadle <vab88011@gmail.com>
Subject:      Re: Contingency Table Testing Within Rows
Comments: To: james.moffitt@thomson.com
In-Reply-To:  <945D579F76FD5741A043511E6FE99B571586718F@TLRUSMNEAGMBX32.ERF.THOMSON.COM>
Content-Type: text/plain; charset="us-ascii"

How was this table produced? Is a case a respondent from a particular survey specifying a particular brand preference? That is, do the row percentages add to 100%

If so, perhaps a column proportion test (requires putting the brands on top and the dates on the side) might give you what you want. This is available from CTABLES.

For each row cell it displays significantly different column cells. Go to Help and select Tables Option>Test Statistics>Comparing Column Proportions for a discussion.

-----Original Message----- From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Jim Moffitt Sent: Wednesday, January 09, 2008 8:49 AM To: SPSSX-L@LISTSERV.UGA.EDU Subject: Contingency Table Testing Within Rows

I have a 5 X 5 contingency table that depicts the percentage of respondents (based to column totals) that prefer each of 5 brands. The 5 brands are the row labels. The column labels are different survey dates so Column 1 is Fall 2007, Column 2 is Fall 2006, Column 3 is Fall 2005, etc. Thus, cell 1 (matrix element 11) contains the proportion of Fall 2007 respondents that preferred Brand A, the next cell to the right (matrix element 12) contains the proportion of Fall 2006 respondents that prefer Brand A, the next cell to the right (matrix element 13) contains the proportion of Fall 2005 respondents that prefer Brand A, etc.

Each survey was administered to a different random sample, so the column samples are independent of each other.

What significance test would I apply to identify significant differences within the rows while controlling for family-wise probability issues? In other words, I'm looking for a test that will test within the row vectors so I can say matrix element 11 is significantly different from 14 and 15, matrix element 14 is significantly different from 13 and 15, matrix element 22 is significantly different from 24 , matrix element 34 is significantly different from 31, 33, and 35, etc.

How would I run such a test in SPSS 14.0?

Do I need a specific SPSS module like Advances Tests to run the required test?

Thanks for your help.

======= To manage your subscription to SPSSX-L, send a message to LISTSERV@LISTSERV.UGA.EDU (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 LISTSERV@LISTSERV.UGA.EDU (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


Back to: Top of message | Previous page | Main SPSSX-L page