Date: Wed, 22 Nov 2006 14:58:14 -1000
Reply-To: Bob Schacht <schacht@hawaii.edu>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Bob Schacht <schacht@hawaii.edu>
Subject: Re: Still the Significance test question
In-Reply-To: <20061123004007.46645.qmail@web54510.mail.yahoo.com>
Content-Type: text/plain; charset=us-ascii; format=flowed
At 02:40 PM 11/22/2006, OZGU GILL wrote:
>Hi there,
>
> I have sent a message yesterday to the list. I'm little bit impatient
> before the Thanks Giving holiday, since I need to finish this project and
> this is one part of it.
Perhaps it is because you haven't given us enough information.
> My question was: I want prepare a significance test between two years
> in a survey question. there are # of responses tallied for each choice or
> classes. Let say
>
> 2005 2006
>
> Choice A 15 25
> Choice B 30 45
> Choice C 20 30
> Choice D 40 65 etc.
What does this mean?
* That in 2005, 15 people made Choice A, 30 made Choice B, etc.?
* Are these choices independent or contingent? That is, do people get
to choose A OR B OR C OR D, or can they choose any combination?
> It looks like when I put them in a graph there is a significant
> difference between 2005 and 2006 for Choice D.
* Why does the difference between 2005 & 2006 appear to you to be
"significant," whereas the others do not? That is, what is it about the 40
and 65 that seems more significant to you?
>What kind of test should I use in SPSS? I'm confused here and I have no
>one to ask. Thanks in advance.
If you can give us more information, perhaps we can help you.
Bob
Robert M. Schacht, Ph.D. <schacht@hawaii.edu>
Pacific Basin Rehabilitation Research & Training Center
1268 Young Street, Suite #204
Research Center, University of Hawaii
Honolulu, HI 96814
