A few things

1)  Why have you categorized age ?  I hesitate to use the word 'never'
with regard to statistical analyses, but this is RARELY a good idea, and
only when you have strong substantive reasons for doing so.  There are
numerous papers demonstrating this, but, briefly, suppose that your age
categories are
0-12  13-18 19-24 25-65 66 and over

then you are saying that a 12 year old is just like a 2 year old, and
very different from a 13 year old.  

If your data was given to you categorized like this, and you don't have
access to the original data, then you have my sympathy.

2) Given ordered data (like the cateogires of age) there are better
methods than the usual chi-square.  This chi-square ignores the ordering
of the data, and treats it as categorical (so, if you had categories
like 'race' or 'religion' where there is no natural ordering, they would
be appropriate).

To do this simply, I would use a test for trend.

3) I would LOOK at the freqencies and see what there is to see.   You
might want to post the 5 x 2 table here - then WE could see what you are
looking at.

HTH

Peter

Peter L. Flom, PhD
Assistant Director, Statistics and Data Analysis Core
Center for Drug Use and HIV Research
National Development and Research Institutes
71 W. 23rd St
www.peterflom.com
New York, NY 10010
(212) 845-4485 (voice)
(917) 438-0894 (fax)



>>> [EMAIL PROTECTED] 4/30/2004 9:17:12 AM >>>
Hi, 

I think I've mastered the chi square test, but not too sure about its
outcome and if I have used it appropriately.

I have 5 age groups with yes/no response data, is a 5x2 chi square
test the test to choose to check for differences between age groups
for the question?

I have found no statistical significant difference  by completeing
this table(i.e. the chi value was not high enough for the p=0.5
threshold).  Can I say the yes/no responses between age groups are not
statistically different?

Thanks for any help, it will be most appreciated, Katie x
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to