NONMEM Users Network Archive

Hosted by Cognigen

RE: Bayesian estimation example

From: Bhattaram, Atul <atul.bhattaram>
Date: Thu, 12 Apr 2007 08:47:12 -0400

Hello Tausif

One of the many ways to analyze the data you have:

1. Understand the structural model in healthy volunteers using the
average concentration-time data using WinNonlin for example.
2. Use these estimates as your initial parameters and run MAXEVAL=0 =
NONMEM and see how the predictions are (This will give you some idea
about the data from patients and your starting model).
3. You can fix some of the parameters (for example ka) and estimate
the parameters of interest.

If your drug has long half-life and the samples that you have are drawn
at pre-dose, then you can use a simpler model (Css=F*Dose/(CL*Tau)) =
estimate CL.

With data from 200 patients and 2 or 3 samples (depending on when they
were collected), I think you should be able to estimate the parameters
of interest. You don't need any specific control stream for Bayesian
for this purpose. Regular control stream in NONMEM should work for you.


Venkatesh Atul Bhattaram
US Food and Drug Administration

"The contents of this message are mine personally and do not necessarily
reflect any position of the Government or the Food and Drug

-----Original Message-----
From: owner-nmusers
On Behalf Of Tausif Ahmed
Sent: Thursday, April 12, 2007 7:03 AM
To: nmusers
Subject: RE: [NMusers] Bayesian estimation example

Dear Group members,

I will make my objective more clear- I have a drug X in which I have
information in healthy volunteers with extensive sampling done, single
dose (12-14 samples).

I have data on appx. 100 volunteers at different dose levels from phase
I studies.

We also have a data in 16 patients at one dose only, with extensive

Now we have data from 200 patients, with 2-3 blood samples collected
from each patient at different doses.
It is also seen that the PK changes in patients.
What I am interested is that can we use Bayesian estimates, (and I think
posthoc estimate from NONMEM, as Yaning mentions) to determine the
pharmacokinetics (PK) of the whole population from these 2-3 blood
samples collected per patient.
Hope it is more clear.
I have checked at website- ( suggested by many
but could not find any control stream on Bayesian. Can the group help me
on this.
I thank the experts for giving their comments on the same.

Tausif Ahmed Ph.D.
Metabolism and Pharmacokinetics Department

Ranbaxy Research Lab India

-----Original Message-----
From: Wang, Yaning [

Sent: Wednesday, April 11, 2007 8:30 PM
To: Nick Holford; Tausif Ahmed
Subject: RE: [NMusers] Bayesian estimation example

Tausif may be referring to the posthoc estimate from NONMEM (empirical
Bayesian estimate).

-----Original Message-----
From: owner-nmusers
On Behalf Of Nick Holford
Sent: Wednesday, April 11, 2007 10:43 AM
To: Tausif Ahmed
Cc: nmusers
Subject: Re: [NMusers] Bayesian estimation example


Why do you want to use Bayesian Estimation? If you have only just
started to use NONMEM then perhaps you have misunderstood the reasons
for using it. It is very rarely needed.


> Dear Group members,

> I have recently started using NONMEM for population analysis.
> I need you help in understanding Bayesian estimation using NONMEM.
> Can any body provide me a sample control stream along with data file
(Excel or csv format) and also explain the output.
> I use Visual NM to run NONMEM version V.

> Thanking you in anticipation.

> Regards
> Tausif Ahmed Ph.D.
> Metabolism and Pharmacokinetics Department Ranbaxy Research Lab India

Nick Holford, Dept Pharmacology & Clinical Pharmacology University of
Auckland, 85 Park Rd, Private Bag 92019, Auckland, New Zealand

(i) The information contained in this e-mail message is intended only
for the confidential use of the recipient(s) named above. This message
is privileged and confidential. If the reader of this message is not the
intended recipient or an agent responsible for delivering it to the
intended recipient, you are hereby notified that you have received this
document in error and that any review, dissemination, distribution, or
copying of this message is strictly prohibited. If you have received
this communication in error, please notify us immediately by e-mail, and
delete the original message.


 (ii) The sender confirms that Ranbaxy shall not be responsible if this
email message is used for any indecent, unsolicited or illegal purposes,
which are in violation of any existing laws and the same shall solely be
the responsibility of the sender and that Ranbaxy shall at all times be
indemnified of any civil and/ or criminal liabilities or consequences

Received on Thu Apr 12 2007 - 08:47:12 EDT

The NONMEM Users Network is maintained by ICON plc. Requests to subscribe to the network should be sent to:

Once subscribed, you may contribute to the discussion by emailing: