Back to the Top
The following message was posted to: PharmPK
Dear All
Precise assays are frequently rejected when i use the standard Parallel
line regression approach.
I have picked out a stement from a paper (see below). Has anyone come
across some sort of policy (or acceptance criteria) based on sound
statistical grounds on accepting assays with "high" precision.
Comments on such an approach will be highly appreciated.
Regards Vince
'It is important to avoid any automatic rule of rejecting assays on
account of non-linearity or other aspects of statistical invalidity. As
Humphrey et al [1953] have emphasised, a rule based solely on
individual significance tests would merely result in the most precise
assays being rejected ! A truly linear regression is a rarity, and to
penalise all assays in which high precision detects non-linearity is a
folly. To formulate an ideal policy is difficult ....'
Back to the Top
The following message was posted to: PharmPK
Dear All,
Linear line regression is sometimes misleading. We proved this in this
article for methotrexate in detail.
Non-linear heteroscedastic regression model for determination of
methotrexate in human plasma by high-performance liquid chromatography,
Sadray et al.Journal of chromatography B,787(2003)293-302.
Sadray, PhD
Back to the Top
The following message was posted to: PharmPK
Dear Vince:
"A new parallelism acceptance criterion for validating large plate
bioassay results"
Story M., Winson J., Beyer P and Boehm G.
Journal of Biological Standardization (1986) 14, 249-254.
is an interesting paper about the subject.
Silvia
PharmPK Discussion List Archive Index page
Copyright 1995-2010 David W. A. Bourne (david@boomer.org)