Dear nmusers,
I am currently analyzing PK profiles after a single iv adminstration.
Volunteers were sampled frequently: 12 samples per curve.
For the structural model 2- and a 3-compartment models are compared. The CWRES
vs time plot of the 2-compartment shows the typical wave, indicative for a
3-compartment model. Introduction of a third compartment eliminated the wave,
OFV decreased with 180 points, precision of the estimates did change notably,
but the condition number increased from 998 to 2.0*E16.
Does anyone know how to interpret this large increase in condition number?
Best wishes,
Laureen ten Berg
[Beschrijving: cid:[email protected]]
Laureen ten Berg-Lammers
Hospital Pharmacist
Academisch Medisch Centrum
Universiteit van Amsterdam
Meibergdreef 9 | 1105 AZ Amsterdam | Room: M01-224
Tel: +31(0)20-5662726 | Pager *62726 | [email protected]
________________________________
AMC Disclaimer : https://www.amc.nl/disclaimer
________________________________
nonmem question regarding condition number
Hi Laureen,
Large condition numbers (typically interpreted as >1000) indicate that two or
more parameters in the model are highly correlated in their covariance and that
the model parameters are difficult to identify. Given your description below,
I would not suggest using the 3-compartment model (even with its 180 point
reduction in OFV) because two of your parameters are so highly correlated that
the condition number is reaching the level of computational precision (2E16 is
very large for a condition number). I'd also look at the NONMEM output to see
if the 3-compartment model had any errors around the convergence.
Thanks,
Bill
Quoted reply history
From: [email protected] [mailto:[email protected]] On
Behalf Of L.A. ten Berg - Lammers
Sent: Thursday, March 24, 2016 6:10 AM
To: '[email protected]'
Subject: [NMusers] nonmem question regarding condition number
Dear nmusers,
I am currently analyzing PK profiles after a single iv adminstration.
Volunteers were sampled frequently: 12 samples per curve.
For the structural model 2- and a 3-compartment models are compared. The CWRES
vs time plot of the 2-compartment shows the typical wave, indicative for a
3-compartment model. Introduction of a third compartment eliminated the wave,
OFV decreased with 180 points, precision of the estimates did change notably,
but the condition number increased from 998 to 2.0*E16.
Does anyone know how to interpret this large increase in condition number?
Best wishes,
Laureen ten Berg
[Beschrijving: cid:[email protected]]
Laureen ten Berg-Lammers
Hospital Pharmacist
Academisch Medisch Centrum
Universiteit van Amsterdam
Meibergdreef 9 | 1105 AZ Amsterdam | Room: M01-224
Tel: +31(0)20-5662726 | Pager *62726 |
[email protected]<mailto:[email protected]>
________________________________
AMC Disclaimer : https://www.amc.nl/disclaimer
________________________________
Hi Laureen,
When a condition number exceeding 1000 is indicative of severe ill
conditioning, which means that you model ?is over-parameterized?.
Please check these links:
http://www.cognigencorp.com/nonmem/nm/99may012003.html
http://www.cognigencorp.com/nonmem/current/2008-February/4212.html?
Carolina
PhD candidate
________________________________
De: [email protected] <[email protected]> en nombre de
L.A. ten Berg - Lammers <[email protected]>
Enviado: jueves, 24 de marzo de 2016 20:10
Para: '[email protected]'
Asunto: [NMusers] nonmem question regarding condition number
Dear nmusers,
I am currently analyzing PK profiles after a single iv adminstration.
Volunteers were sampled frequently: 12 samples per curve.
For the structural model 2- and a 3-compartment models are compared. The CWRES
vs time plot of the 2-compartment shows the typical wave, indicative for a
3-compartment model. Introduction of a third compartment eliminated the wave,
OFV decreased with 180 points, precision of the estimates did change notably,
but the condition number increased from 998 to 2.0*E16.
Does anyone know how to interpret this large increase in condition number?
Best wishes,
Laureen ten Berg
[Beschrijving: cid:[email protected]]
Laureen ten Berg-Lammers
Hospital Pharmacist
Academisch Medisch Centrum
Universiteit van Amsterdam
Meibergdreef 9 | 1105 AZ Amsterdam | Room: M01-224
Tel: +31(0)20-5662726 | Pager *62726 | [email protected]
________________________________
AMC Disclaimer : https://www.amc.nl/disclaimer
________________________________
Hi Lauren,
my first guess would be that you do not need as many ETAs as you had before
when using 3 compartments. May you also added TAs on the 3rd compartments'
parameter? Either way, please check for overparametrization as Caroline
indicated, perferably starting with the ETAs.
Kind regards
Sven Mensing
Quoted reply history
2016-03-24 11:10 GMT+01:00 L.A. ten Berg - Lammers <
[email protected]>:
> Dear nmusers,
> I am currently analyzing PK profiles after a single iv adminstration.
> Volunteers were sampled frequently: 12 samples per curve.
> For the structural model 2- and a 3-compartment models are compared. The
> CWRES vs time plot of the 2-compartment shows the typical wave, indicative
> for a 3-compartment model. Introduction of a third compartment eliminated
> the wave, OFV decreased with 180 points, precision of the estimates did
> change notably, but the condition number increased from 998 to 2.0*E16.
> Does anyone know how to interpret this large increase in condition number?
> Best wishes,
> Laureen ten Berg
>
>
>
> *[image: Beschrijving: cid:[email protected]]*
>
>
>
>
>
> *Laureen ten Berg-Lammers*
>
> Hospital Pharmacist
>
>
>
> Academisch Medisch Centrum
>
> Universiteit van Amsterdam
>
>
>
>
>
> Meibergdreef 9 | 1105 AZ Amsterdam | Room: M01-224
>
> Tel: +31(0)20-5662726 | Pager *62726 | *[email protected]
> <[email protected]>*
>
>
>
>
>
> ------------------------------
>
> AMC Disclaimer : https://www.amc.nl/disclaimer
> ------------------------------
>
>
Dear Laureen,
High condition number represents overparametrization. You must check also the
correlation matrix for potential correlations above 0.95 between parameters. If
you strongly feel on the biological basis that your drug is a 3 compartment
model, then you may fix some of the parameters of 3 compartment model such as
Q1,Q2 based on prior data and estimate other parameters to see if your
diagnostics make sense. Parameters with high SEs could be your clues to the
problems. In my opinion, you have informative data with 12 samples per
subjects(hopefully at the informative time points) to have a complex model.
Best Regards,
Ayyappa
Quoted reply history
> On Mar 24, 2016, at 5:10 AM, L.A. ten Berg - Lammers
> <[email protected]> wrote:
>
> Dear nmusers,
> I am currently analyzing PK profiles after a single iv adminstration.
> Volunteers were sampled frequently: 12 samples per curve.
> For the structural model 2- and a 3-compartment models are compared. The
> CWRES vs time plot of the 2-compartment shows the typical wave, indicative
> for a 3-compartment model. Introduction of a third compartment eliminated the
> wave, OFV decreased with 180 points, precision of the estimates did change
> notably, but the condition number increased from 998 to 2.0*E16.
> Does anyone know how to interpret this large increase in condition number?
> Best wishes,
> Laureen ten Berg
>
>
> <image001.gif>
>
>
> Laureen ten Berg-Lammers
> Hospital Pharmacist
>
> Academisch Medisch Centrum
> Universiteit van Amsterdam
>
>
> Meibergdreef 9 | 1105 AZ Amsterdam | Room: M01-224
> Tel: +31(0)20-5662726 | Pager *62726 | [email protected]
>
>
> AMC Disclaimer : https://www.amc.nl/disclaimer
>
Hi Laureen,
If you want an objective second opinion then make likelihood profiles for both
models.
I expect a very shallow one for at least one maybe two parameters for the
3-compartment model and thus the parameters are not estimated accurately, even
if the objective function goes down.
good luck,
Douglas Eleveld
Quoted reply history
________________________________
From: [email protected] [[email protected]] on behalf of
L.A. ten Berg - Lammers [[email protected]]
Sent: Thursday, March 24, 2016 11:10 AM
To: '[email protected]'
Subject: [NMusers] nonmem question regarding condition number
Dear nmusers,
I am currently analyzing PK profiles after a single iv adminstration.
Volunteers were sampled frequently: 12 samples per curve.
For the structural model 2- and a 3-compartment models are compared. The CWRES
vs time plot of the 2-compartment shows the typical wave, indicative for a
3-compartment model. Introduction of a third compartment eliminated the wave,
OFV decreased with 180 points, precision of the estimates did change notably,
but the condition number increased from 998 to 2.0*E16.
Does anyone know how to interpret this large increase in condition number?
Best wishes,
Laureen ten Berg
[Beschrijving: cid:[email protected]]
Laureen ten Berg-Lammers
Hospital Pharmacist
Academisch Medisch Centrum
Universiteit van Amsterdam
Meibergdreef 9 | 1105 AZ Amsterdam | Room: M01-224
Tel: +31(0)20-5662726 | Pager *62726 | [email protected]
________________________________
AMC Disclaimer : https://www.amc.nl/disclaimer
________________________________
________________________________
Dear Laureen,
I recommend that you determine with exploratory plotting how strong the
evidence for the 3-compartment behavior is (eg. in semi-log plots: is 3 cpt
behavior present in most subjects? are inflection points reasonably collocated?
how do slope changes relate to measurement noise? etc.).
If you do see strong evidence for 3 cpt behavior and have a biological
rationale for a third compartment, I wouldn't just drop the 3 cpt model
because of a high condition number in the model you tested, especially since
you said that precision did not deteriorate.
The fact that the 2 cpt model was borderline ill-conditioned (998 ~ 1000) with
serially sampled IV data suggests that the 2 cpt model was already
over-parameterized. My recommendation is to simplify the 2 cpt model (eg. by
simplifying random structure, looking for large entries in correlation matrix
or RSEs, ...) and then run the comparison again.
Herbert
Quoted reply history
From: [email protected] [mailto:[email protected]] On
Behalf Of Denney, William S.
Sent: Thursday, March 24, 2016 6:53 AM
To: L.A. ten Berg - Lammers; '[email protected]'
Subject: [NMusers] RE: nonmem question regarding condition number
EXTERNAL
Hi Laureen,
Large condition numbers (typically interpreted as >1000) indicate that two or
more parameters in the model are highly correlated in their covariance and that
the model parameters are difficult to identify. Given your description below,
I would not suggest using the 3-compartment model (even with its 180 point
reduction in OFV) because two of your parameters are so highly correlated that
the condition number is reaching the level of computational precision (2E16 is
very large for a condition number). I'd also look at the NONMEM output to see
if the 3-compartment model had any errors around the convergence.
Thanks,
Bill
From: [email protected]<mailto:[email protected]>
[mailto:[email protected]] On Behalf Of L.A. ten Berg - Lammers
Sent: Thursday, March 24, 2016 6:10 AM
To: '[email protected]'
Subject: [NMusers] nonmem question regarding condition number
Dear nmusers,
I am currently analyzing PK profiles after a single iv adminstration.
Volunteers were sampled frequently: 12 samples per curve.
For the structural model 2- and a 3-compartment models are compared. The CWRES
vs time plot of the 2-compartment shows the typical wave, indicative for a
3-compartment model. Introduction of a third compartment eliminated the wave,
OFV decreased with 180 points, precision of the estimates did change notably,
but the condition number increased from 998 to 2.0*E16.
Does anyone know how to interpret this large increase in condition number?
Best wishes,
Laureen ten Berg
[Beschrijving: cid:[email protected]]
Laureen ten Berg-Lammers
Hospital Pharmacist
Academisch Medisch Centrum
Universiteit van Amsterdam
Meibergdreef 9 | 1105 AZ Amsterdam | Room: M01-224
Tel: +31(0)20-5662726 | Pager *62726 |
[email protected]<mailto:[email protected]>
________________________________
AMC Disclaimer : https://www.amc.nl/disclaimer
________________________________