Dear all,
I am working on this pop PK analysis. the objective is, to explore some
covariates on the exposure.
the dataset has rich sampled study, with absorption phase well captured. and
also sparse sampling study with only trough sample, and another sample around
1-2hr after dosing
with rich sample study data, the ka and eta on Ka is well estimated using FOCE
INT method and 1ct 1st order model.
but when with pooled dataset, using the same model and method, eta on Ka is
estimated to be almost 0, the fit to the data from rich sampled study became
little worse on the peak.
Is there way to keep a good estimation of Eta on Ka, which is to make sure
the good capture of Cmax, at least for rich sampled subjects?
with my limited knowledge, I was thinking:
-- fixing Eta on ka with the estimate from rich sample study alone
-- hybrid estimating methods
-- nonparametric method
Any comments will be highly appreciated.
estimating Ka from dataset combining rich sample study and sparse sampling study
Dear Ethan,
Your first suggestion would be a pragmatic way of moving forward.
I have no personal experience with the hybrid method.
Your third suggestion, using a full non-parametric approach
should work better and is mathematically more consistent.
This approach should not suffer from shrinkage.
I would expect this algorithm to behave as follows:
1) The subjects with rich data should be essentially completely
unaffected by the subjects with sparse data.
2) The subjects with sparse data should have posterior (i.e. intra-individual)
probability distributions of Ka which are similar to the inter-individual
distribution of Ka for the population of subjects with rich data.
Depending on how the distribution of individual Ka values of
the subjects with rich data look, you may or may not get a
multimodal intra-individual distribution of Ka for the patients
with sparse data. This may become important for the covariate
relationships which you are trying to develop subsequently.
Please let me know, if Roger's group or I can be of help to set
you up, if you want to use NPAG for solving this task.
Best wishes
Juergen
Quoted reply history
From: [email protected] [mailto:[email protected]] On
Behalf Of Ethan Wu
Sent: Wednesday, June 17, 2009 11:21 AM
To: [email protected]
Subject: [NMusers] estimating Ka from dataset combining rich sample study and
sparse sampling study
Dear all,
I am working on this pop PK analysis. the objective is, to explore some
covariates on the exposure.
the dataset has rich sampled study, with absorption phase well captured. and
also sparse sampling study with only trough sample, and another sample around
1-2hr after dosing
with rich sample study data, the ka and eta on Ka is well estimated using FOCE
INT method and 1ct 1st order model.
but when with pooled dataset, using the same model and method, eta on Ka is
estimated to be almost 0, the fit to the data from rich sampled study became
little worse on the peak.
Is there way to keep a good estimation of Eta on Ka, which is to make sure
the good capture of Cmax, at least for rich sampled subjects?
with my limited knowledge, I was thinking:
-- fixing Eta on ka with the estimate from rich sample study alone
-- hybrid estimating methods
-- nonparametric method
Any comments will be highly appreciated.
You can try
IF(RICH data) THEN
KA=THETA(1)*EXP(ETA(1))
ELSE
KA=THETA(1)
ENDIF
--------------------------------------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web: www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel: (301) 767 5566
Ethan Wu wrote:
> Dear Juergen,
>
> thanks for your comment. I was actually not aware such full non-parametric approach, apology for my ignorance. the approach is very intersting, I will try to understand it more. with regards to non-parametric approach, I was thinking alone the line of estimation method for Eta only as offered in nonmem. so I went ahead tried $NONPARAMETRIC UNCONDITIONAL option, but the Eta for Ka still estimated to be very small, 5.50E-08 vs 0.13 estimated by using rich data only.
>
> ------------------------------------------------------------------------
> *From:* Jurgen Bulitta <[email protected]>
> *To:* Ethan Wu <[email protected]>
>
> *Cc:* " [email protected] " < [email protected] >; Roger Jelliffe < [email protected] >; "Neely, Michael" < [email protected] >
>
> *Sent:* Wednesday, June 17, 2009 2:42:31 PM
>
> *Subject:* RE: [NMusers] estimating Ka from dataset combining rich sample study and sparse sampling study
>
> Dear Ethan,
>
> Your first suggestion would be a pragmatic way of moving forward.
>
> I have no personal experience with the hybrid method.
>
> Your third suggestion, using a full non-parametric approach
>
> should work better and is mathematically more consistent.
>
> This approach should not suffer from shrinkage.
>
> I would expect this algorithm to behave as follows:
>
> 1) The subjects with rich data should be essentially completely
>
> unaffected by the subjects with sparse data.
>
> 2) The subjects with sparse data should have posterior (i.e. intra-individual)
>
> probability distributions of Ka which are similar to the inter-individual
>
> distribution of Ka for the population of subjects with rich data.
>
> Depending on how the distribution of individual Ka values of
>
> the subjects with rich data look, you may or may not get a
>
> multimodal intra-individual distribution of Ka for the patients
>
> with sparse data. This may become important for the covariate
>
> relationships which you are trying to develop subsequently.
>
> Please let me know, if Roger’s group or I can be of help to set
>
> you up, if you want to use NPAG for solving this task.
>
> Best wishes
>
> Juergen
>
> *From:* [email protected] [ mailto: [email protected] ] *On Behalf Of *Ethan Wu
>
> *Sent:* Wednesday, June 17, 2009 11:21 AM
> *To:* [email protected]
>
> *Subject:* [NMusers] estimating Ka from dataset combining rich sample study and sparse sampling study
>
> Dear all,
>
> I am working on this pop PK analysis. the objective is, to explore some covariates on the exposure.
>
> the dataset has rich sampled study, with absorption phase well captured. and also sparse sampling study with only trough sample, and another sample around 1-2hr after dosing
>
> with rich sample study data, the ka and eta on Ka is well estimated using FOCE INT method and 1ct 1st order model.
>
> but when with pooled dataset, using the same model and method, eta on Ka is estimated to be almost 0, the fit to the data from rich sampled study became little worse on the peak.
>
> Is there way to keep a good estimation of Eta on Ka, which is to make sure the good capture of Cmax, at least for rich sampled subjects?
>
> with my limited knowledge, I was thinking:
>
> -- fixing Eta on ka with the estimate from rich sample study alone
>
> -- hybrid estimating methods
>
> -- nonparametric method
>
> Any comments will be highly appreciated.
Hi Ethan,
If OMEGA(?) for KA is drastically reduced when including the sparse
data, then something is wrong with your model and in this case it is not
the estimation method or assumption on distribution of individual
parameter). Eta-shrinkage would not drastically reduce the estimate of
OMEGA, since this estimate is driven by the subjects/studies which
contain information on the parameter.
If the sparse data is multiple dosing it may be that KA is variable
between occasions, rather than between subjects (assuming the sparse
data contain some information on KA). Or if the sparse data is from a
less well-controlled study or a different population, it may be that
increased IIV in other parts of the model (e.g. OMEGA on V) is making
IIV in KA appear low for the rich study, when fitting the two studies
together. If you get the covariate model in place this problem will be
solved. For the simple model you have it should be quick to start out
assuming that most parameters (THETAs and OMEGAs) are different between
the two studies and then reduce down to a model which is stable and
parsimonious. Obviously, if you eventually can explain the differences
using more mechanistic covariates than study number that is of more use.
Cheers
Jakob
Dear Ethan,
Variances estimated to be zero may result from fixing off-diagonal variances
to zero (i.e. not using BLOCKs in IIV). Here, however, it may be that there
are systematic differences between the sparse and the rich data experiments.
Maybe fasting/fed status or something else is different. If the fit to the
rich data is markedly worse when including the rich data, at least one
parameter is different between the two situations. I would explore what
parameter(s) that would be. In addition to Jakob's suggestions below, the
two data sets together may indicate a more complex structural model that a
single profile indicated. Maybe you need to go to a two-compartment for
example.
Best regards,
Mats
Mats Karlsson, PhD
Professor of Pharmacometrics
Dept of Pharmaceutical Biosciences
Uppsala University
Box 591
751 24 Uppsala Sweden
phone: +46 18 4714105
fax: +46 18 471 4003
Quoted reply history
From: [email protected] [mailto:[email protected]] On
Behalf Of Ribbing, Jakob
Sent: Wednesday, June 17, 2009 10:43 PM
To: Ethan Wu; Jurgen Bulitta; [email protected]
Cc: Roger Jelliffe; Neely, Michael
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample
study and sparse sampling study
Hi Ethan,
If OMEGA(?) for KA is drastically reduced when including the sparse data,
then something is wrong with your model and in this case it is not the
estimation method or assumption on distribution of individual parameter).
Eta-shrinkage would not drastically reduce the estimate of OMEGA, since this
estimate is driven by the subjects/studies which contain information on the
parameter.
If the sparse data is multiple dosing it may be that KA is variable between
occasions, rather than between subjects (assuming the sparse data contain
some information on KA). Or if the sparse data is from a less
well-controlled study or a different population, it may be that increased
IIV in other parts of the model (e.g. OMEGA on V) is making IIV in KA appear
low for the rich study, when fitting the two studies together. If you get
the covariate model in place this problem will be solved. For the simple
model you have it should be quick to start out assuming that most parameters
(THETAs and OMEGAs) are different between the two studies and then reduce
down to a model which is stable and parsimonious. Obviously, if you
eventually can explain the differences using more mechanistic covariates
than study number that is of more use.
Cheers
Jakob
Dear Ethan
I concur with Mats's comments below.
As a note, from a design perspective adding additional data to an experiment
cannot result in less precise parameter estimates under the assumption that the
individuals from the two data sets are exchangeable. Under this assumption
therefore the Sparse data should merely add information to the Rich data. That
the Sparse data is affecting the parameter estimates from the Rich data
suggests that the two data sets are not exchangeable (different centre,
different assay, different covariates ...).
Another possible way to investigate the differences between the two data sets
would be to analyse them sequentially, perhaps with consideration for using the
analysis from the Rich data as an informative prior for the analysis of the
Sparse data and see where this leads you.
Kind regards
Steve
--
Professor Stephen Duffull
Chair of Clinical Pharmacy
School of Pharmacy
University of Otago
PO Box 913 Dunedin
New Zealand
E: [email protected]<mailto:[email protected]>
P: +64 3 479 5044
F: +64 3 479 7034
Design software: http://www.winpopt.com
Quoted reply history
From: [email protected] [mailto:[email protected]] On
Behalf Of Mats Karlsson
Sent: Thursday, 18 June 2009 9:17 a.m.
To: 'Ribbing, Jakob'; 'Ethan Wu'; 'Jurgen Bulitta'; [email protected]
Cc: 'Roger Jelliffe'; 'Neely, Michael'
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample study
and sparse sampling study
Dear Ethan,
Variances estimated to be zero may result from fixing off-diagonal variances to
zero (i.e. not using BLOCKs in IIV). Here, however, it may be that there are
systematic differences between the sparse and the rich data experiments. Maybe
fasting/fed status or something else is different. If the fit to the rich data
is markedly worse when including the rich data, at least one parameter is
different between the two situations. I would explore what parameter(s) that
would be. In addition to Jakob's suggestions below, the two data sets together
may indicate a more complex structural model that a single profile indicated.
Maybe you need to go to a two-compartment for example.
Best regards,
Mats
Mats Karlsson, PhD
Professor of Pharmacometrics
Dept of Pharmaceutical Biosciences
Uppsala University
Box 591
751 24 Uppsala Sweden
phone: +46 18 4714105
fax: +46 18 471 4003
From: [email protected] [mailto:[email protected]] On
Behalf Of Ribbing, Jakob
Sent: Wednesday, June 17, 2009 10:43 PM
To: Ethan Wu; Jurgen Bulitta; [email protected]
Cc: Roger Jelliffe; Neely, Michael
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample study
and sparse sampling study
Hi Ethan,
If OMEGA(?) for KA is drastically reduced when including the sparse data, then
something is wrong with your model and in this case it is not the estimation
method or assumption on distribution of individual parameter). Eta-shrinkage
would not drastically reduce the estimate of OMEGA, since this estimate is
driven by the subjects/studies which contain information on the parameter.
If the sparse data is multiple dosing it may be that KA is variable between
occasions, rather than between subjects (assuming the sparse data contain some
information on KA). Or if the sparse data is from a less well-controlled study
or a different population, it may be that increased IIV in other parts of the
model (e.g. OMEGA on V) is making IIV in KA appear low for the rich study, when
fitting the two studies together. If you get the covariate model in place this
problem will be solved. For the simple model you have it should be quick to
start out assuming that most parameters (THETAs and OMEGAs) are different
between the two studies and then reduce down to a model which is stable and
parsimonious. Obviously, if you eventually can explain the differences using
more mechanistic covariates than study number that is of more use.
Cheers
Jakob
Dear all,
I agree that this kind of behaviour suggests there is some problem with
the model (most likely a lack of exchangeability). I think the ideas
suggested are all good, but the first thing I would try is to separate
residual noise for the two studies with an indicator variable. It is
likely that study procedures, precision of recorded sampling times etc.
vary between the two studiess.
Best regards, James
James G Wright PhD
Scientist
Wright Dose Ltd
Tel: 44 (0) 772 5636914
Quoted reply history
-----Original Message-----
From: [email protected] [mailto:[email protected]]
On Behalf Of Stephen Duffull
Sent: 18 June 2009 07:04
To: Mats Karlsson; 'Ribbing, Jakob'; 'Ethan Wu'; 'Jurgen Bulitta';
[email protected]
Cc: 'Roger Jelliffe'; 'Neely, Michael'
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample
study and sparse sampling study
Dear Ethan
I concur with Mats's comments below.
As a note, from a design perspective adding additional data to an
experiment cannot result in less precise parameter estimates under the
assumption that the individuals from the two data sets are exchangeable.
Under this assumption therefore the Sparse data should merely add
information to the Rich data. That the Sparse data is affecting the
parameter estimates from the Rich data suggests that the two data sets
are not exchangeable (different centre, different assay, different
covariates ...).
Another possible way to investigate the differences between the two data
sets would be to analyse them sequentially, perhaps with consideration
for using the analysis from the Rich data as an informative prior for
the analysis of the Sparse data and see where this leads you.
Kind regards
Steve
--
Professor Stephen Duffull
Chair of Clinical Pharmacy
School of Pharmacy
University of Otago
PO Box 913 Dunedin
New Zealand
E: [email protected]
P: +64 3 479 5044
F: +64 3 479 7034
Design software: www.winpopt.com
From: [email protected] [mailto:[email protected]]
On Behalf Of Mats Karlsson
Sent: Thursday, 18 June 2009 9:17 a.m.
To: 'Ribbing, Jakob'; 'Ethan Wu'; 'Jurgen Bulitta';
[email protected]
Cc: 'Roger Jelliffe'; 'Neely, Michael'
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample
study and sparse sampling study
Dear Ethan,
Variances estimated to be zero may result from fixing off-diagonal
variances to zero (i.e. not using BLOCKs in IIV). Here, however, it may
be that there are systematic differences between the sparse and the rich
data experiments. Maybe fasting/fed status or something else is
different. If the fit to the rich data is markedly worse when including
the rich data, at least one parameter is different between the two
situations. I would explore what parameter(s) that would be. In addition
to Jakob's suggestions below, the two data sets together may indicate a
more complex structural model that a single profile indicated. Maybe you
need to go to a two-compartment for example.
Best regards,
Mats
Mats Karlsson, PhD
Professor of Pharmacometrics
Dept of Pharmaceutical Biosciences
Uppsala University
Box 591
751 24 Uppsala Sweden
phone: +46 18 4714105
fax: +46 18 471 4003
From: [email protected] [mailto:[email protected]]
On Behalf Of Ribbing, Jakob
Sent: Wednesday, June 17, 2009 10:43 PM
To: Ethan Wu; Jurgen Bulitta; [email protected]
Cc: Roger Jelliffe; Neely, Michael
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample
study and sparse sampling study
Hi Ethan,
If OMEGA(?) for KA is drastically reduced when including the sparse
data, then something is wrong with your model and in this case it is not
the estimation method or assumption on distribution of individual
parameter). Eta-shrinkage would not drastically reduce the estimate of
OMEGA, since this estimate is driven by the subjects/studies which
contain information on the parameter.
If the sparse data is multiple dosing it may be that KA is variable
between occasions, rather than between subjects (assuming the sparse
data contain some information on KA). Or if the sparse data is from a
less well-controlled study or a different population, it may be that
increased IIV in other parts of the model (e.g. OMEGA on V) is making
IIV in KA appear low for the rich study, when fitting the two studies
together. If you get the covariate model in place this problem will be
solved. For the simple model you have it should be quick to start out
assuming that most parameters (THETAs and OMEGAs) are different between
the two studies and then reduce down to a model which is stable and
parsimonious. Obviously, if you eventually can explain the differences
using more mechanistic covariates than study number that is of more use.
Cheers
Jakob
Dear all,
thanks to Mats suggestion, using full cov matrix did assign Eta more
reasonably to Ka, with not very precised estimates
another suggestion is that, there may be some underline difference in the
structure model between sparse MD data, and rich SD -- by visual inspection of
sparse MD data, I really can't think it can support more complext model itself
with 2-3 datapoints per subject in each study period (total of 2), with the
sampling the same across subjects.
another suggestion is that to model study individually, both Ka and IIV on
Ka estimated from sparse sample study were much larger.
so I think I will further pursue exploration of IOV, as Jakob pointed out.
Quoted reply history
________________________________
From: James G Wright <[email protected]>
To: Stephen Duffull <[email protected]>; Mats Karlsson
<[email protected]>; "Ribbing, Jakob" <[email protected]>;
Ethan Wu <[email protected]>; Jurgen Bulitta <[email protected]>;
[email protected]
Cc: Roger Jelliffe <[email protected]>; "Neely, Michael" <[email protected]>
Sent: Thursday, June 18, 2009 6:56:57 AM
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample study
and sparse sampling study
Dear all,
I agree that this kind of behaviour suggests there is some problem with the
model (most likely a lack of exchangeability). I think the ideas suggested are
all good, but the first thing I would try is to separate residual noise for the
two studies with an indicator variable. It is likely that study procedures,
precision of recorded sampling times etc. vary between the two studiess.
Best regards, James
James G WrightPhD
Scientist
Wright Dose Ltd
Tel: 44 (0) 772 5636914
-----Original Message-----
From: [email protected] [mailto:[email protected]] On
Behalf Of Stephen Duffull
Sent: 18 June 2009 07:04
To: Mats Karlsson; 'Ribbing, Jakob'; 'Ethan Wu'; 'Jurgen Bulitta';
[email protected]
Cc: 'Roger Jelliffe'; 'Neely, Michael'
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample study
and sparse sampling study
Dear Ethan
I concur with Mats’s comments below.
As a note, from a design perspective adding additional data to an experiment
cannot result in less precise parameter estimates under the assumption that the
individuals from the two data sets are exchangeable. Under this assumption
therefore the Sparse data should merely add information to the Rich data. That
the Sparse data is affecting the parameter estimates from the Rich data
suggests that the two data sets are not exchangeable (different centre,
different assay, different covariates ...).
Another possible way to investigate the differences between the two data sets
would be to analyse them sequentially, perhaps with consideration for using the
analysis from the Rich data as an informative prior for the analysis of the
Sparse data and see where this leads you.
Kind regards
Steve
--
Professor Stephen Duffull
Chair of Clinical Pharmacy
School of Pharmacy
University of Otago
PO Box 913 Dunedin
New Zealand
E: [email protected]
P: +64 3 479 5044
F: +64 3 479 7034
Design software: www.winpopt.com
From:[email protected] [mailto:[email protected]] On
Behalf Of Mats Karlsson
Sent: Thursday, 18 June 2009 9:17 a.m.
To: 'Ribbing, Jakob'; 'Ethan Wu'; 'Jurgen Bulitta'; [email protected]
Cc: 'Roger Jelliffe'; 'Neely, Michael'
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample study
and sparse sampling study
Dear Ethan,
Variances estimated to be zero may result from fixing off-diagonal variances to
zero (i.e. not using BLOCKs in IIV). Here, however, it may be that there are
systematic differences between the sparse and the rich data experiments. Maybe
fasting/fed status or something else is different. If the fit to the rich data
is markedly worse when including the rich data, at least one parameter is
different between the two situations. I would explore what parameter(s) that
would be. In addition to Jakob’s suggestions below, the two data sets together
may indicate a more complex structural model that a single profile indicated.
Maybe you need to go to a two-compartment for example.
Best regards,
Mats
Mats Karlsson, PhD
Professor of Pharmacometrics
Dept of Pharmaceutical Biosciences
Uppsala University
Box 591
751 24 Uppsala Sweden
phone: +46 18 4714105
fax: +46 18 471 4003
From:[email protected] [mailto:[email protected]] On
Behalf Of Ribbing, Jakob
Sent: Wednesday, June 17, 2009 10:43 PM
To: Ethan Wu; Jurgen Bulitta; [email protected]
Cc: Roger Jelliffe; Neely, Michael
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample study
and sparse sampling study
Hi Ethan,
If OMEGA(?) for KA is drastically reduced when including the sparse data, then
something is wrong with your model and in this case it is not the estimation
method or assumption on distribution of individual parameter). Eta-shrinkage
would not drastically reduce the estimate of OMEGA, since this estimate is
driven by the subjects/studies which contain information on the parameter.
If the sparse data is multiple dosing it may be that KA is variable between
occasions, rather than between subjects (assuming the sparse data contain some
information on KA). Or if the sparse data is from a less well-controlled study
or a different population, it may be that increased IIV in other parts of the
model (e.g. OMEGA on V) is making IIV in KA appear low for the rich study, when
fitting the two studies together. If you get the covariate model in place this
problem will be solved. For the simple model you have it should be quick to
start out assuming that most parameters (THETAs and OMEGAs) are different
between the two studies and then reduce down to a model which is stable and
parsimonious. Obviously, if you eventually can explain the differences using
more mechanistic covariates than study number that is of more use.
Cheers
Jakob
Steve -
I agree with you that adding addtional data (in this case adding a sparse data
set to a dense data set)
ideally should result in better (more precise) estimates when the individuals
from the two data sets
are exchangeable, but only assuming the underlying estimation methodology is
well-behaved for
both the sparse and dense data. In the real world, and in particular
with the FOCE approximation, sparse data may not be well estimated by FOCE and
merging sparse data with
dense data may contaminate the dense data rather than enhance it.
As an example, I ran a simulation using an Emax Hill coefficient model with
gamma=4.5 (this is the same
model that appears in Mats' 2007 Pharm Res paper Hooker et al, "Conditional
Weighted Residuals (CWRES):
A Diagostic For the FOCE Method)". Using dense data (25 observations per
subject) and 200 subjects
simulated from the true model, all parameters all well estimated. In
particular, gamma is estimated at
4.38 (std err = 0.069)
For an equivalent amount of sparse data (2000 subjects, average of 2.5
obs/susbject, also simulated from the same
model and the same design except that observations were removed at random with
a 90% probability of removal for
any given observation), the FOCE estimate of gamma is 3.51 (std err = 0.060)
(all other parameters are reasonably estimated by the sparse data).
When the data sets are combined, the gamma estimate is 3.69 (std err =0.104 )
. Thus merging the dense data with
the sparse data has resulted in a good estimate being converted to a relatively
poor one. Moreover,
the std error (albeit from a Hessian based computation) has increased in the
merged set relative to both
separate individual sets.
I agree with Jurgen that nonparametric estimation is much less susceptible to
this contamination
effect. For the merged data set, the nonparametric
method will likely simply use the sharply defined support points from the
dense data, (assuming there are a reasonable number
of these and they cover the region of interest). Individuals from the dense
data set will be modeled with very large
probabilities associated with their single corresponding support point, while
individuals from the sparse set will
have probabilities spread out over several supports.
Bob Leary
Robert H. Leary, PhD
Fellow
Pharsight - A Certara(tm) Company
5625 Dillard Dr., Suite 205
Cary, NC 27511
Phone/Voice Mail: (919) 852-4625, Fax: (919) 859-6871
Email: [email protected]
This email message (including any attachments) is for the sole use of the
intended recipient and may contain confidential and proprietary information.
Any disclosure or distribution to third parties that is not specifically
authorized by the sender is prohibited. If you are not the intended recipient,
please contact the sender by reply email and destroy all copies of the original
message.
Quoted reply history
-----Original Message-----
From: [email protected] [mailto:[email protected]]on
Behalf Of Stephen Duffull
Sent: Thursday, June 18, 2009 2:4 AM
To: Mats Karlsson; 'Ribbing, Jakob'; 'Ethan Wu'; 'Jurgen Bulitta';
[email protected]
Cc: 'Roger Jelliffe'; 'Neely, Michael'
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample study
and sparse sampling study
Dear Ethan
I concur with Mats's comments below.
As a note, from a design perspective adding additional data to an experiment
cannot result in less precise parameter estimates under the assumption that the
individuals from the two data sets are exchangeable. Under this assumption
therefore the Sparse data should merely add information to the Rich data. That
the Sparse data is affecting the parameter estimates from the Rich data
suggests that the two data sets are not exchangeable (different centre,
different assay, different covariates ...).
Another possible way to investigate the differences between the two data sets
would be to analyse them sequentially, perhaps with consideration for using the
analysis from the Rich data as an informative prior for the analysis of the
Sparse data and see where this leads you.
Kind regards
Steve
--
Professor Stephen Duffull
Chair of Clinical Pharmacy
School of Pharmacy
University of Otago
PO Box 913 Dunedin
New Zealand
E: <mailto:[email protected]> [email protected]
P: +64 3 479 5044
F: +64 3 479 7034
Design software: http://www.winpopt.com www.winpopt.com
From: [email protected] [mailto:[email protected]] On
Behalf Of Mats Karlsson
Sent: Thursday, 18 June 2009 9:17 a.m.
To: 'Ribbing, Jakob'; 'Ethan Wu'; 'Jurgen Bulitta'; [email protected]
Cc: 'Roger Jelliffe'; 'Neely, Michael'
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample study
and sparse sampling study
Dear Ethan,
Variances estimated to be zero may result from fixing off-diagonal variances to
zero (i.e. not using BLOCKs in IIV). Here, however, it may be that there are
systematic differences between the sparse and the rich data experiments. Maybe
fasting/fed status or something else is different. If the fit to the rich data
is markedly worse when including the rich data, at least one parameter is
different between the two situations. I would explore what parameter(s) that
would be. In addition to Jakob's suggestions below, the two data sets together
may indicate a more complex structural model that a single profile indicated.
Maybe you need to go to a two-compartment for example.
Best regards,
Mats
Mats Karlsson, PhD
Professor of Pharmacometrics
Dept of Pharmaceutical Biosciences
Uppsala University
Box 591
751 24 Uppsala Sweden
phone: +46 18 4714105
fax: +46 18 471 4003
From: [email protected] [mailto:[email protected]] On
Behalf Of Ribbing, Jakob
Sent: Wednesday, June 17, 2009 10:43 PM
To: Ethan Wu; Jurgen Bulitta; [email protected]
Cc: Roger Jelliffe; Neely, Michael
Subject: RE: [NMusers] estimating Ka from dataset combining rich sample study
and sparse sampling study
Hi Ethan,
If OMEGA(?) for KA is drastically reduced when including the sparse data, then
something is wrong with your model and in this case it is not the estimation
method or assumption on distribution of individual parameter). Eta-shrinkage
would not drastically reduce the estimate of OMEGA, since this estimate is
driven by the subjects/studies which contain information on the parameter.
If the sparse data is multiple dosing it may be that KA is variable between
occasions, rather than between subjects (assuming the sparse data contain some
information on KA). Or if the sparse data is from a less well-controlled study
or a different population, it may be that increased IIV in other parts of the
model (e.g. OMEGA on V) is making IIV in KA appear low for the rich study, when
fitting the two studies together. If you get the covariate model in place this
problem will be solved. For the simple model you have it should be quick to
start out assuming that most parameters (THETAs and OMEGAs) are different
between the two studies and then reduce down to a model which is stable and
parsimonious. Obviously, if you eventually can explain the differences using
more mechanistic covariates than study number that is of more use.
Cheers
Jakob