NONMEM Users Network Archive

Hosted by Cognigen


From: Paul Matthew Westwood <pwestwood02>
Date: Tue, 22 Jul 2008 14:49:18 +0100

From: Paul Matthew Westwood
Sent: 22 July 2008 13:20
To: Nick Holford
Subject: RE: [NMusers] PPC


Thanks for your reply and apologies once again for another confusing email.=
 I think I am using VPC, which as I understand it is simulating n datasets =
using the final parameter estimates gained from the final model, and then t=
aking the median and 90% confidence interval (for example) for each simulat=
ed concentration and comparing these to the real concentrations. Whereas, P=
PC is where you then run the final model through the simulated datasets and=
 compare selected statistics of these new runs with the original. Is this c=
orrect? You mentioned including uncertainty on the parameter estimates in t=
he simulated datasets. Would one usually not include uncertainty (fixing th=
e error terms to zero) in the simulated datasets? Doing this with mine obvi=
ously produced much better concentrations with no negative values and no 's=
ignificant' outliers. Another thing you mentioned is comparing the median o=
f the simulated concentrations with the median of the original dataset conc=
entrations, but as there is only one sample for any particular time point w=
ould this indicate the unsuitability of VPC (and furthermore PPC) for this =

Thanks again,
From: owner-nmusers
 Of Nick Holford [n.holford
Sent: 22 July 2008 10:30
To: nmusers
Subject: Re: [NMusers] PPC


Its not clear to me if you did a VPC (visual predictive check) using
just the final estimates of the parameters) or tried to do a posterior
predictive check (PPC) including uncertainty on the parameter estimates
in the simulation.

I dont have any experience with PPC but I dont think its helpful for
model evaluation. Its more of a tool for understanding uncertainties of
predictions for future studies.

I assume you dont have complications like informative dropout processes
to complicate the simulation so if you did a VPC and the median of the
predictions doesnt match the median of the observations then your model
needs more work.

Some negative concs are OK but 'impossibly high values' point to
problems with your model.

So I think you can safely say the VPC has worked very well -- it has
told you that you need to think more about your model. You might find
some ideas in these references:

1. Tod M, Jullien V, Pons G. Facilitation of drug evaluation in
children by population methods and modelling. Clin Pharmacokinet.
2. Anderson BJ, Holford NH. Mechanism-Based Concepts of Size and
Maturity in Pharmacokinetics. Annu Rev Pharmacol Toxicol. 2008;48:303-32.


Paul Matthew Westwood wrote:
> Hello all,
> I wonder if someone can give me some tips on PPC.
> I am working on a midazolam dataset with a pediatric population, and have=
 decided to use PPC as a model validation technique. The dataset I am model=
ling has up to 43 patients, at different ages, different weights, different=
 times of dosing and sampling, and different doses. I simulated 100 dataset=
s using NONMEM VI, fixing all parameters to the final estimates from the mo=
del. The simulated datasets produced had a large proportion of negative con=
centrations, and also a few impossibly large concentration values. Also the=
 median, 5th and 95th percentiles were not very promising, and the resultin=
g graphs not very clean.
> Firstly, can I use PPC with any degree of confidence with a dataset such =
as this, and if so, do I omit the negative concentration values from the an=
> Thanks in advance for any help given.
> Paul Westwood,
> PhD Student,
> QUB,
> Belfast.

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

Received on Tue Jul 22 2008 - 09:49:18 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: