Home > Statistics Every Writer Should Know > The Stats Board > Discusssion
Re: Is the chi-square appropriate?
Message posted by Annie on May 2, 2000 at 12:00 AM (ET)
I am studying the pacing of a group
of 3 bears. I have been looking at
the data in terms of time pacing per
total observation time. I would like to
determine if a decrease in pacing after
one bear became pregnant is significant.
The problem I am having is that my
total n's are different. For example:
Pacing before=300 after=200
no pacing before=400 after=400
my chi-sqare values do not seem right -
they are huge! Help! Is there a better
test to use?
READERS RESPOND:
(In chronological order. Most recent at the bottom.)
Re: Re: Is the chi-square appropriate?
Message posted by bill on May 3, 2000 at 12:00 AM (ET)
It depends. Is your data in terms of counts? Chi-Squared test is appropriate for categorical data only. Other tests are available for you, including Fisher' Exact Test as well as others. Make sure you set-up your contingency table correctly for your test.
Your $5 contribution helps cover part the $500 annual cost of keeping this site online.