Back to the Top
Hi,
I am new to the field of pharmacokinetic modelling and model
evaluation and would appreciate any comments on the issue of residual
analysis. When you statistically test on a normal distribution as an
add-on to goodness-of-fit plots and which test would you recommend? I
thought that the D'Agostino Pearson Test might be a good option to
further distinguish between models if the residuals are similiarly
well distributed. Can anyone help on this topic and maybe suggest some
papers in which residuals where not only assessed graphically but also
statistically tested on a normal distribution?
Cheers, Winnie
Back to the Top
The following message was posted to: PharmPK
Dear Winnie,
F-test is another test which is used for distinguishing nested models.
Apart from this we can compare different models using standard
criteria's like Minimum objective function value, AIC, SBC or SSR (Sum
of squared residuals) or WSSR (Weighted Sum of squared residuals).
Thanks and regards
Dr. Tausif Ahmed
Metabolism and Pharmacokinetics Department
Ranbaxy, India
Back to the Top
[The next few email messages were sent on Friday but I didn't have
access to email so they may be 'out-of-order' relative to items
submitted over the weekend - db]
The following message was posted to: PharmPK
Dear Winnie,
Akaike's information Criterion (AIC) can also be used to compare
different models. For this please refer to this article.
"Application of Akaike's information Criterion (AIC) in the Evaluation
of Linear pharmacokinetic equations" Journal of pharmacokinetics and
Biopharmaceutics, Vol. 6, No. 2, 1978.
By Kiyoshi Yamaoka, Terumichi Nakagawa, and Toyozo Uno
I hope this will help.
Thanks and Regards,
Ravi
Thanks & Regards,
Ravi Shankar Pandey
Assistant Biostatistician - ADDR
Panacea Biotec Ltd.
Sampann R & D,
Ambala-Chandigarh Highway,
P.O. Lalru - 140501, Punjab, India.
Email - ravipandey.-at-.panaceabiotec.com
Want to post a follow-up message on this topic?
If this link does not work with your browser send a follow-up message to PharmPK@boomer.org with "Residual analysis - Test on normality" as the subject | Support PharmPK by using the |
Copyright 1995-2011 David W. A. Bourne (david@boomer.org)