Calling all statisticians...
Steve Hilliard (hilliard@zookeeper.zoo.uga.edu)
Tue, 31 Aug 93 09:05:22 EDT
As the subject line indicates, I need some stats advice. I've got a major
user that has spent a lot of time working on a project exploring the
utility of increased CV as an indicator of genetic damage (on the
population level in animals). They've done dozens of experiments to make
sure they've accounted for staining variability, etc. The problem is, now
that this student's committee is reviewing the work, one member say you
can't do ANOVA's on the CV's to test for differences between the treatment
groups. He says that since CV is a ratio, it can't be analyzed by ANOVA,
unless the numerator and denominator are unrelated. Obviously SD and MEAN
are related--that's why we calculate CV. I've suggested she talk to
members of our stats dept. but does anyone have any feelings/prior
experience on this subject. Is there some other approach that would be
valid?
Thanks in advance for any replies,
sgh
Steve G. Hilliard |
Cell Analysis Facility, Univ. of GA | I brew the beer I drink!
(706) 542-9474 hilliard@zookeeper.zoo.uga.edu| Let's have a tasting
These opinions are mine--get your own! | at Lake Placid!
CD ROM Vol 2 was produced by staff at the Purdue University Cytometry Laboratories
and distributed free of charge as an educational service to the cytometry community.
If you have any comments please direct them to Dr. J. Paul Robinson, Professor & Director, PUCL,
Purdue University, West Lafayette, IN 47907. Phone:(317) 494-0757; FAX (317) 494-0517; Web http://www.cyto.purdue.edu
EMAIL robinson@flowcyt.cyto.purdue.edu
