Re: Bioequivalence question
From: LSheiner <lewis@c255.ucsf.edu>
Subject: Re: Bioequivalence question
Date: Fri, 13 Nov 1998 11:06:18 -0800
As I understand it, the original rulewas 80-120, based onthe idea that a 20% deviation would in geenral be biologically unimportant. It was changed to 80-125 to be symmetric on the log scale where most stat tests are done.