Histogram Statistics
lori_m@SMTPGATE.BCSEW.EDU
Wed, 27 Dec 95 13:31:56 CST
Happy New Year!
I'm posting for a colleague with a statistics question:
The basic question is this... If you overlay two histograms and do a
K/S statistical analysis, it will give you a % probability that the
curves are different. This has been used to show that binding in the
experiment has occurred. If you want to show that binding has NOT
occurred or has been blocked, at what level of probability can you say
that the two curves are NOT different?
How do you prove both that binding has occurred (two curves are
different) and that you have now been able to block binding (two
curves are not different)?
Are people out there using other statistics to show this? What type
of numbers show statistical significance in your results?
I haven't seen much in publications about interpretation of data like
this. Feel free to reply directly to me or post back to the group.
Thanks in advance for the help!
Lorie
_____________________________________________________________________
Lorie Miller
FACS Core Lab
Blood Center of Southeastern Wisconsin
lori_m@smtpgate.bcsew.edu
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
