Chi-square test?

[Byrd Sellers, Johnita]

Hello All,

 

I am trying to double check my work to make sure that my interpretations
are valid and correct.  I have the following problem:

 

*       A person can go to one of four different meeting types, we will
call them M1, M2, M3, and M4
*       After a person attends the meeting, they have to specify their
attitude towards the meeting.  Their attitude can be negative, neutral
or positive

 

The purpose of the analysis is to determine the meeting types that had
the positive attitudes.  The hypothesis is that people rated M1 and M2
higher than the other meeting types.  So, we want to show that there is
a difference between the two groups.  Then, we want to show that M1 and
M2 are rated higher than M3 and M4 (combined).  Last, we want to show
that this difference is significant.  I have chose to use a chi-square
test to show that there is a significant difference.  Each group is
independent and the number of people within each group is not the same.

 

The results seem to come to the appropriate conclusions but I just
wanted to make sure that this test would be appropriate to use.  Is this
test correct or should I be using the Mann-Whitney test?  Or is there
another test that would best analyze this problem?

 

Thanks in advance for all of your help.

 

Johnita

 

====================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

[Swank, Paul R]

I would say that if a person can go to only one meeting then the
chi-square test would be appropriate. The non-parametric procedures
would have many ties so I can't see an advantage over the chi square
test here, particularly if you collapse negative and neutral opinions so
that you are comparing positive versus not positive. Of course, since
people can choose which meeting to go to, it may be that people who are
more positive are more likely to select meeting types 1 and 2. So you
are not going to be able to state conclusively that meeting types 1 and
2 are more positive unless you can randomly assign people to one meeting
type.

Paul R. Swank, Ph.D.
Professor and Director of Research
Children's Learning Institute
University of Texas Health Science Center - Houston


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Byrd Sellers, Johnita
Sent: Tuesday, June 10, 2008 9:46 AM
To: [hidden email]
Subject: Chi-square test?

Hello All,



I am trying to double check my work to make sure that my interpretations
are valid and correct.  I have the following problem:



*       A person can go to one of four different meeting types, we will
call them M1, M2, M3, and M4
*       After a person attends the meeting, they have to specify their
attitude towards the meeting.  Their attitude can be negative, neutral
or positive



The purpose of the analysis is to determine the meeting types that had
the positive attitudes.  The hypothesis is that people rated M1 and M2
higher than the other meeting types.  So, we want to show that there is
a difference between the two groups.  Then, we want to show that M1 and
M2 are rated higher than M3 and M4 (combined).  Last, we want to show
that this difference is significant.  I have chose to use a chi-square
test to show that there is a significant difference.  Each group is
independent and the number of people within each group is not the same.



The results seem to come to the appropriate conclusions but I just
wanted to make sure that this test would be appropriate to use.  Is this
test correct or should I be using the Mann-Whitney test?  Or is there
another test that would best analyze this problem?



Thanks in advance for all of your help.



Johnita



==========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