NONMEM Users Network Archive

Hosted by Cognigen

RE: OFV or Diagnostic Plot ?? Which one rules...

From: Nick Holford <n.holford>
Date: Wed, 13 Feb 2019 08:20:21 +0000

Hi Sumeet,
So I think you should work on learning how to create a VPC so you can really understand if your model is predicting anything useful. There are several tools available (e.g. PSN, WFN). Don’t you have a supervisor who can help you do these basic things?
Best wishes,

Nick Holford, Professor Clinical Pharmacology
Dept Pharmacology & Clinical Pharmacology, Bldg 503 Room 302A
University of Auckland,85 Park Rd,Private Bag 92019,Auckland,New Zealand
office:+64(9)923-6730 mobile:NZ+64(21)46 23 53 FR+33(6)62 32 46 72
email: n.holford
Read the question, answer the question, attempt all questions

From: Singla, Sumeet K <sumeet-singla
Sent: Wednesday, 13 February 2019 8:35 PM
To: Nick Holford <n.holford
Cc: nmusers
Subject: Re: OFV or Diagnostic Plot ?? Which one rules...

Dr. Holford,

I don’t have VPC for now as my R code for that is not ready. I read somewhere that additive residual error model can be applied if concentrations spread over less than one order of magnitude. What do you think about it?
Sumeet Singla

On Feb 13, 2019, at 12:49 AM, Nick Holford <n.holford
Hi Sumeet,
The OFV is often king. But what does the VPC look like? That is the gold standard. Diagnostic plots are equivalent to Rorschach blots.
If you find a way to let us see the VPCs then we can all enjoy the view.
Best wishes,

Holford NHG. The visual predictive check – superiority to standard diagnostic (Rorschach) plots Last accessed 13 Feb 2019. PAGE. 2005;14.
Nguyen TH, Mouksassi MS, Holford N, Al-Huniti N, Freedman I, Hooker AC, et al. Model Evaluation of Continuous Data Pharmacometric Models: Metrics and Graphics. CPT: pharmacometrics & systems pharmacology. 2017;6(2):87-109.

From: owner-nmusers<mailto:owner-nmusers
Sent: Wednesday, 13 February 2019 7:28 PM
To: nmusers sers
Subject: [FORGED] [NMusers] OFV or Diagnostic Plot ?? Which one rules...

Hi Everyone,

I am fitting two compartment PK model to Marijuana (THC) concentrations. When I apply proportional error (or proportional plus additive) residual model, I get pretty good fits (except 15% of subjects) at all time points.
However, when I apply only additive error residual model, I get perfect fits in all subjects but objective functional value is increased by about 20 units. DV vs IPRED reveal all concentrations on line of unity.
My question is: should I go with additive error model which gives me perfect fit but higher OFV or should I go with proportional error model which gives me lower OFV but not so good fit in couple of subjects?

Sumeet Singla
Graduate Student
Dpt. of Pharmaceutics & Translational Therapeutics
College of Pharmacy- University of Iowa

Received on Wed Feb 13 2019 - 03:20:21 EST

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: