Date: Mon, 6 Jan 1997 12:24:52 +1000
Reply-To: R Wong <r.wong@CCLRU.UNSW.EDU.AU>
Sender: "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From: R Wong <r.wong@CCLRU.UNSW.EDU.AU>
Subject: Ratios or difference
Content-Type: text/plain; charset=us-ascii
I would greatly aprreciate if anybody can tell me if
there exists a theoretical basis for using "ratios" rather than
"difference" between a test and control value when testing two groups of
subjects. An example is in Ophthalmic drug delivery wherein the
"residence time" of a test vehicle and control are measured in humans on
a given day. The goal is to use the control value to reduce the
variability since there is substantial day-to-day intrasubject and
intersubject variability. Typical measures (for ratioing or subtraction)
would be ACU (Activiy vs time), and the rate constants of elimination.
Any ideas or references ?
Thanks for your help..