From: Ramalingam Sankaran sankaram@Stanford.Edu
Subject: [NMusers] Estimation Methods-HELP!!
Date: Fri, March 19, 2004 10:42 am
Dear All:
I wonder if any of you could suggest a publication or a text-book that
would help someone WITHOUT much math. background,to understand the
estimation methods(the first order, FOCE, hybrid etc.,).The Users guide
seem a little daunting, and my search for a basic work to understand the
concept and applications has not been fruitful.
Will be grtaeful for any sugesstions.
Thanks a lot
Ram
Estimation Methods-HELP!!
From: Bhattaram, Atul BhattaramA@cder.fda.gov
Subject: RE: [NMusers] Estimation Methods-HELP!!
Date: Fri, March 19, 2004 10:51 am
Hello Ram
In my experience to understand the estimation methods etc it is better to
start with fundamentals on probability theory, regression. To understand the
Maximum likelhood principles etc I would recommend you to attend statistics
courses in your university.
Venkatesh Atul Bhattaram
CDER, FDA.
From: Howard Lee hl8@georgetown.edu
Subject: RE: [NMusers] Estimation Methods-HELP!!
Date: Fri, March 19, 2004 11:07 am
Dear Ram,
I found the following book very useful.
Rice,J.A., Mathematical Statistics and Data Analysis, Duxbury Press, 1995,
ISBN (0-534-20934-3)
Hope this helps. Thank you.
Howard Lee, MD, PhD
Assistant Professor
Center for Drug Development Science
Department of Pharmacology, Georgetown University
School of Medicine, Box 571441
Washington, DC 20057-1441
USA
Tel: 202-687-8198
Fax: 202-687-0193
From: Wang, Yaning WangYA@cder.fda.gov
Subject: RE: [NMusers] Estimation Methods-HELP!!
Date: Fri, March 19, 2004 11:25 am
The following book is an excellent resource after you learn enough
statistics.
"Nonlinear Models for Repeated Measurement Data" by Marie Davidian and David
M. Giltinan, Chapman & Hall, ISBN 0-412-98431-9
Yaning Wang
OCPB,FDA
From: Melvin S. Munsaka, PhD mmunsaka@tgrd.com
Subject: RE: [NMusers] Estimation Methods-HELP!!
Date: Fri, March 19, 2004 12:59 pm
The following documents may also be useful. Unfortunately, I cannot promise "WITHOUT
much math"
as requested by Ram. I think the math cannot be avoided.
http://tal.stat.umu.se/~gb/winter/homepage/nonmem.paper.pdf
http://www4.stat.ncsu.edu/~davidian/timegoesby_handout.pdf
http://www4.stat.ncsu.edu/~davidian/nlmmreview.pdf
Melvin S. Munsaka, PhD
Senior Statistician
Takeda Global Research and Development Center, Inc
Biometrics and Data Management, Statistics Dept
475 Half Day Road
Lincolnshire, IL 60069
Phone (Direct): 847-383-7390
Phone (Toll Free): 877-872-3700 x 7390
Fax (Business): 847-383-3501
E-mail: mmunsaka@tgrd.com
From: Bachman, William (MYD) bachmanw@iconus.com
Subject: RE: [NMusers] Estimation Methods-HELP!!
Date: Mon, March 22, 2004 9:28 am
I would recommend first reading the FDA Guidelines for population analysis
(free off the web). Getting a bit dated but it's a good overview of the
topic and the references are the seminal historical papers in the field. If
you don't like math, this is not the best area to work in.
I would also recommend putting a subject on your emails. Many people often
assume an email without a topic is spam and auto-delete it.
From: Vladimir Piotrovsky, Ph.D. VPIOTROV@PRDBE.jnj.com
Subject: RE: [NMusers] Estimation Methods-HELP!!
Date: Mon, March 22, 2004 11:45 am
Ram,
I recommend two textbooks:
Vonesh EF and Chinchilli VM. Linear and nonlinear models for the analysis of
repeated measurements. Marcell Dekker, 1996. ISBN 0-8247-8248-8
Pinheiro JC and Bates DM. Mixed-effects in S and S-PLUS. Springer, 2000.
ISBN 0-387-98957-9
The first one is somewhat similar to Davidian and Guiltinan's book, but
gives a good math and stat introduction useful for a novice. Although
Pinheiro and Bates' book is about S language and has no relation to NONMEM,
it is useful to understand e.g. hypothesis testing associated with
mixed-effects modeling.
Best regards,
Vladimir
-----------------------------------------------------------------
Vladimir Piotrovsky, Ph.D.
Research Fellow, Advanced PK-PD Modeling & Simulation
Global Clinical Pharmacokinetics and Clinical Pharmacology
Johnson & Johnson Pharmaceutical Research & Development
Turnhoutseweg 30
B-2340 Beerse
Belgium
_______________________________________________________