Paul,
One immediate problem is S3=VB; most likely, you need S4=VB since you
observations are in compartment 4
Also, you do not have observations in A2 in the sample data set. If you do have them elsewhere, you
need to define S2 as well.
Why would you use ADVAN9 (nonlinear) rather than ADVAN5
ese, but
I cannot figure out how to model the intravascular esterase inactivation
of drug without using the differentials.
Leonid Gibiansky wrote:
Paul,
One immediate problem is S3=VB; most likely, you need S4=VB since you
observations are in compartment 4
Also, you do not have observations
need to scale it again using VB.
Hope that helps.
Manoj
*/Leonid Gibiansky <[EMAIL PROTECTED]>/* wrote:
Paul,
One immediate problem is S3=VB; most likely, you need S4=VB since
you observations are in compartment 4
Also, you do not have observations in A2 in the sample da
Dear All,
Could anyone help me to interpret ETAbar p value? I have:
TOT. NO. OF OBS RECS:1486
TOT. NO. OF INDIVIDUALS: 213
ETABAR: -0.52E-02 -0.27E-01 -0.93E-01
P VAL.: 0.90E+00 0.24E+00 0.81E-04
ETA1 ETA2 ETA3
ETA1 4.08E-01
ETA2 2.26E-01 2.31E-01
ETA3 0.0
]
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On
Behalf Of Leonid Gibiansky
Sent: Tuesday, February 20, 2007 18:25
To: nmusers@globomaxnm.com
Subject: [NMusers] ETABAR p-value
Dear All,
Could anyone help me to interpret ETAbar p value? I have
I am not sure that you can answer this question in general, without seeing the data. It may depend
on the ratio of inter- to intra- individual errors. I would try it. One option could be to fix the
variances of residual errors at values obtained from the full-profile subject. Also, you will need
I cannot see any problems with the equations, looks correct to me:
K=CL1/V1
DADT1=-K*A(1)
S1=V1
etc.
Leonid
Nick Holford wrote:
Sam,
There is no problem with using CL1 in this code. This is not a reserved word
and CL is not a required variable name when using $DES.
I fixed the more obvious e
Since theoretically rescaling should not matter, the problem is in details that can not be extracted
from the description without seeing the data and control stream. Just as an experiment (and to check
your data creation process) run the model with the data where AMT and DV are rescaled by a fact
"The method with interaction does not work due to the small sample size."
I do not think that this is correct. Sample size should not be an issue for FOCEI. If you have lag
time with random effect, this could be a problem for FOCE, but not the sample size.
Leonid
[EMAIL PROTECTED] wrote:
Hell
Should not be a problem for oral administration. If IV, make sure that trough observation records
are before the dosing records (time can be the same, but they should be ordered correctly).
Leonid
Ying HONG wrote:
Dear NMusers,
A single-dose of drug was given to healthy volunteers and a PK mo
TIME is not reset, it is counted from the first dose in this example. To describe the model you need
to introduce TAD (time after the most recent dose) into the data set and use it for FLAG reset:
IF(TAD.GT.LAG) FLAG=1
Same with occasion, it would be best to introduce variable OCC (occasion, 1
In Nonmem V (and VI as well), you can put a unit dose to compartment 1, and then estimate
"bioavailability" F1
F1=THETA(...)*EXP(ETA(...))
In Nonmem VI, you can directly supply initial conditions to the compartmental amounts via parameter
A_0(1), e.g.,
A_0(1)=THETA(...)*EXP(ETA(...))
(see h
Use S2=V/1000 instead of S1=V/1000
Leonid
Tausif Ahmed wrote:
Dear All,
I am new to the field of POP-PK.
We are developing a POP-PK model for our in-house drug. The conc. are in
ng/mL and dose is in mg.
The drug is administered *orally* and follows *1-compartment* model. It
has a short hal
If it is indeed similar, one can try to solve is with the similar trick, forcing all etas to work
for all subjects:
http://www.metrumrg.com/publications/aaps_2004_etabug.pdf
Leonid
Brian M. Sadler wrote:
Dear Tom,
How does it differ from the parametric problem of non-influential
corre
Nick,
I am not sure that the entire idea is correct: subject can only belong to one population, it cannot
jump from population to population. Therefore, time dependent P() should not be allowed.
Record-number dependence in $MIX was probably invented to have an option of defining the Ps either
b
would
be time varying. In the example proposed in the NONMEM help the covariate
proposed for use in $MIX is AGE. If AGE is properly recorded in the data set
then AGE is guaranteed to be a time varying covariate!
Nick
Leonid Gibiansky wrote:
Nick,
I am not sure that the entire idea is correct: s
not shift from one distribution to another (as explained in
the example above).
Nick
Leonid Gibiansky wrote:
Nick,
I think you are reading it incorrectly. I would guess that for a long-term
study you may relate
probability of response to either baseline age or to the end-of-study age, or
t
Hi Nick,
In R, use mvrnorm (load package MASS first)
In S+, use rmvnorm
Leonid
--
Leonid Gibiansky
President
QuantPharm LLC
www.quantpharm.com
Nick Holford wrote:
Hi,
Can someone give me some clues on how to sample from a multivariate normal
PRED should be used for comparison.
6. You data set lists observation compartment as CMT=8, is this
correct(given the two-compartment model)?
Leonid
--
Leonid Gibiansky
President
QuantPharm LLC
www.quantpharm.com
[EMAIL PROTECTED] wrote
Hi Live,
In terms of GOF, look on the eta distributions (histograms and Q-Q
plots): they should be centered and reasonably normal. Look on eta
correlation (ETAs vs ETAs plots): they should be in agreement with
correlations in your OMEGA matrix. Look on DV vs PRED: there should be
no obvious bi
1 14 2.2 0 179.4 0 0 0
If the interval between two last doses is exactly II=6, then both
variants are equally good; otherwise, the second one could be a little
better
Leonid
---
Leonid Gibiansky
President
QuantPharm LLC
www.quantpharm.com
Ganesh
Hi Nick,
It would help if you prepare a cleaner example that demonstrate the
problem. What exactly are you trying to achieve (A(?)=?). A(1) and A(2)
are not initialized in the code below, so they are zeros as they should.
Is this about A3, A4?
If yes, the problem could be in communication bet
fixed then I would suggest that an extra state be added to the
$AEINITIAL INIT variable. If INIT=-1 then this would mean to obtain a solution
at time=0 and not bother to obtain solutions at subsequent times (for
computational efficiency).
Nick and Carl
Leonid Gibiansky wrote:
Hi Nick,
It would h
; combined error model
Leonid
--
Leonid Gibiansky, President
QuantPharm LLC: www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel: (301) 767 5566
James G Wright wrote:
If Y is the original observed data, then the log-transformed error model is
LOG (Y) = LOG
James,
Note that EVID=4 at those time points, so they could not influence
variance of the residual error, and do not influence parameter estimates.
Leonid
James G Wright wrote:
In regard to Navin's original problem, the most likely cause (in most
datasets) is that you have some very small F's
y big numbers when F is small, I expect this method would
perform worse than working on the original scale.
Best regards, James
James G Wright PhD
Scientist
Wright Dose Ltd
Tel: 44 (0) 772 5636914
www.wright-dose.com
-Original Message-
From: Leonid Gibiansky [mailto:[EMAIL PROT
797
[4,]0079
> det(aa)
[1] -2945
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Sam Liao wrote:
Dear NONMEM users:
Can someon
+1 need to be computed and replaced by a particular number, X is the
number of elements required for implementation of PRIOR)
etc
$TABLE ...COM(x+1)=G11 ..
I have not used this combination, so this is the untested idea.
Leonid
------
Leonid Gibiansky, Ph.D.
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
John Mondick wrote:
I would like to get some feedback from the group concerning the reporting of
modeling results. I have a
the non-normalized set with the initial
conditions closer to the solution (if you choose to use non-normalized
problem as the final model).
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at
nsistent with John's
statements.
Best regards,
Jeroen
J. Elassaiss-Schaap
Scientist PK/PD
Organon NV
PO Box 20, 5340 BH Oss, Netherlands
Phone: + 31 412 66 9320
Fax: + 31 412 66 2506
e-mail: [EMAIL PROTECTED]
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
On B
.
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Tim Bergsma wrote:
Metrum Institute and Random Technologies LLC are pleased to announce the
availability of th
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
-
$PRED
CE=PROP ; define exposure: concentration, AUC or anything else
;PD
EMAX=THETA(1)*EXP
not think that it is correct to initialize A(2)
with 1 if you do not have IV dose=1 at TIME=0.
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
[EMAIL
A(8)
$TABLE ID TIME CMAX TMAX CC2 CC7 CC8
The last record of each patient should provide desired values.
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
P
bservation per embryon, it is unlikely that you can
distinguish between intra and inter subject variability, so I would put
everything to noise (sigma).
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGi
and assigning bioavailability (Nonmem V and VI) or (with
Nonmem VI) using A_0(1)= etc. statements
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Samtani, Ma
http://www.cognigencorp.com/nonmem/current/2007-July/0335.html
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Mark Sale - Next Level Solutions wrote:
I'm thinking
Hi Rik,
$COV PRINT=E
should give you correlation matrix of the
population parameter estimates
As far as I know, there is no way to get SE (and hence covariance
matrix) for individual parameter estimates (ETA values).
Leonid
--
Leonid Gibiansky, Ph.D
% for OMEGAs, as it should
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Paul Westwood wrote:
Dear All,
I'm working on a one-compartment iv model. I
*THETA(3)+THETA(4))
Y=F*(1+SQRT(THETA(3))*ERR(1))+SQRT(THETA(4))*ERR(2).
also, if you take the square of SE% in thetas, you will see that it
nearly matches SE% for SIGMAs, as it should
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Ribbing, Jakob wrote:
Hi all,
I think that Paul stumbled on a rather important issue. The SE of the residual
= FALSE, invisible = TRUE)
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Nick Holford wrote:
Dave,
Have you tried using the minimized option for the R
output (error messages if any)
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Jian Xu wrote:
Dear all,
I did a Pop PK a year ago in NM V, and got a stable model
ian(temp200v2) # -1.956067
median(temp1000) # -1.966652
median(temp10) # -1.959679
sd(temp200) # 0.1984375
sd(temp200v2) # 0.2052445
sd(temp1000)# 0.08406183
sd(temp10) # 0.008499137
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www
(correlated, as a vector)
instead of PK parameters, and compute PK parameters based on the
expected patient covariates.
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
/about/major/nhanes/nh3data.htm
Data can be sampled from this collection, or if needed, described in a
parametric way to sample from a derived distribution.
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail
explained)
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Paul Collier wrote:
Please could someone explain why I get very different results when using
ADVAN3
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
andreas lindauer wrote:
Dear NMusers,
I have a question regarding simulations for a VPC. When a combined
residual error is used it happens that
dependence of CL on WT (if any is noticeable) for very young kids could
be attributed to maturation and explained by AGE covariate
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel
, it
is not a substitute for the real data. Even with optimal design of the
pediatric study (with the same 20 subjects, 3 optimal sample points) I
bet you would gain by using adult data as well.
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web
optimal. I think one should use both datasets together (in the
specific case that was described) and it looks like we are in agreement
on this point.
Regards,
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail
difference gradually declined.
Apart from the times when the rate of concentration changes was very
high (concentration changed significantly within 1-2 minutes) the
difference between arterial and venous concentrations was negligible.
Leonid
--
Leonid Gibiansky
rt can be omitted. Or you can use separate errors
for each CMT:
> Y1=F+F*EPS(1)
> Y2=F+F*EPS(2)
> Y=R1*Y1+R2*Y2
--
S2= V2 should help to get SE. If not, try MATRIX=S on $COV line.
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:
Huali
Even if it gives a good fit, S2=V1 is still an error. You may try to
assume that V2=V1, and then S2=V2=V1, it is fine, but in the current
form, equations are incorrect
Thanks
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web
failure.
Thanks
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Mark Sale - Next Level Solutions wrote:
General question:
What are practical limits on
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Mark Sale - Next Level Solutions wrote:
Leonid,
This isn't PK, and the model show basically the right shape, and the
data suggest reaso
covariates (such as study, dose, weight as necessary, etc.).
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
[EMAIL PROTECTED] wrote:
Dear Dr. Holford
graphically and using
various PK-PD models.
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Fatemeh Akhlaghi, PhD wrote:
Dear NMusers group:
I am puzzled by the
uences
the run time. Is it better (in terms of the run time) to use standard
sizes, or "big" is OK if you have enough RAM?
Thanks!
Leonid
----------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.c
capabilities. I think the OS manages to put active problems to RAM and
non-active ones to swap space so that overall performance is not
affected, but I am not sure, hence the question.
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web
.
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
[EMAIL PROTECTED] wrote:
Dear NM_Users,
we have all been good students and listened to Nick when he told us
again and again the rock-solid
same equation as
DADT(1)= -C1*VM'/(KM+C1) - K10*A(1)
then
DADT(1)= -A(1)*(VM'/V1)/(KM+C1) - K10*A(1)
VM' is indeed should be scaled as WT**0.75 (thus leading to VM scaled as
WT**(-0.25).
Leonid
------
Leonid Gibiansky, Ph.D.
President, Qua
(within the dose/concentration range of your data)
Leonid Gibiansky, Ekaterina Gibiansky,Tarundeep Kakkar, Peiming Ma,
Approximations of the Target-Mediated Drug Disposition Model and
Identifiability of Model Parameters, PAGE 17 (2008) Abstract 1269
[www.page-meeting.org/?abstract=1269]
http
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
[EMAIL PROTECTED] wrote:
Hello NONMEM Users,
Subjects received IV infusion (study 2), IV injection or SQ injection
(study1). In
the simplest, most reasonable and the most-often
used option).
Thanks
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Nick Holford wrote:
Xia,
There is no
cannot be repeated, so your covariate (occasion) will have
different value (level) at any future trial.
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Nick
The next level of random effects can be introduced in NONMEM using PRIOR
subroutine. It existed as undocumented feature even in Nonmem V. Now (in
Nonmem VI) it is official (see help).
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web
Hi Bill,
I think, description in $PRIOR and nwpri help entries are the most
helpful. The simplest 1-compartment problem example is below.
Good luck!
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at
. If they are OK than I would not worry
about ETABAR. However, small ETABAR p-value often hints that the ETA
distribution is not symmetric, or has outliers (non-symmetric long tails).
Thanks
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web
THETA(2)
Thanks
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Xia Li wrote:
Hi Nick,
My pleasure!
This is a topic from Bayesian Hierarchical Model(BHM). If we
e you ever used in your report/publication FINAL model that did
not converge (YES/NO):
8. Define yourself as novice/intermediate/experienced Nonmem user:
Thanks
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LG
the poll beyond this simple statement. In addition, questions
4-7 will help us to understand how widespred is the use of models with
failed convergence step and/or with failed minimization step.
Thanks
Leonid
------
Leonid Gibiansky, Ph.D.
President, Qua
-pasted after the summary
of replies.
Part 3: CSV file with the original data is copy-pasted after the comments
Part 4: R code that I used to summarize the results is provided
Thanks to all who participated.
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm
DADT(1) = -K*A(1) ; plasma C1=A(1)/V1
DADT(2) = K2*A(1)-K23*A(2) ;"transit"(can be duplicated to increase delay)
DADT(3) = K23*A(3)-K30*A(3) ; intracellular C3=A(3)/V3
Thanks
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPha
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Xiao, Alan wrote:
Dear All,
I know this is an old topic, too, but would like to see the statistics.
When you have a dataset with
nce:
TVCL=THETA(X)*(WT/70)**0.75+THETA(Y)*CRCL
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Bonate, Peter wrote:
I have an interesting question I'd like to
dels on CL for each level of renal function?
The suggestion was to define the renal disease as categorical variable,
and then correct CL, for example:
TCL ~ THETA(1) (for healthy)
TCL ~ THETA(2) (for patients with severe renal impairment)
Thanks
Leonid
----------
Leoni
categorical description does not show
any renal impairment effect, it makes no sense to use more complicated
models, and it makes sense to explain dependence of CL on CRCL by WT,
AGE or other available covariates.
Best
Leonid
--
Leonid Gibiansky, Ph.D
Jakob,
The model that I mentioned is not additive; it is multiplicative:
Parameter= MeanValue*Effect1(WT)*Effect2(RF)
but the effect of RF is expressed as a linear function of RF
Effect2(RF) = 1 + THETA()*RF
Leonid
--
Leonid Gibiansky, Ph.D.
President
.
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Ribbing, Jakob wrote:
Leonid,
As I understand the linear model you suggested it can be simplified* to
this structure:
THETA(1)*((W
missing VS=V2,
VA=V3 somewhere.
Thanks
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Dong-Seok Yim wrote:
>
> Hi, colleagues,
>
> I am current
.
Thanks
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Dong-Seok Yim wrote:
Leonid,
Thank you for your comprehensive comment.
Once I raised this, I wish to ask
files needed to run nonmem (in R, use setwd(NonmemDirName) to do it)
Leonid
--
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 users,
I am trying
eads to l(t) below.
As to the 0 to 1 restriction, l(t) is the density, not probability. It
should integrate to one but can be smaller or greater than 1 (any
positive number).
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.qua
parameters, this use of the inverse variance-covariance matrix is
somewhat limited.
--
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Bachman, William wrote:
As a cla
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
SIMON Nicolas wrote:
Hi All,
We have a dataset with as many dosing (amount and length of infusion) as
patients. Once the final model was defined, I
to get higher doses in this
design).
Thanks
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
SIMON Nicolas wrote:
Hi Leonid,
Thanks for your help.
The
estimates): you can
find the poster on PAGE web site. Still, for several real data sets,
I've seen that the log-transformed model provided slightly better fit,
especially for data with large residual error.
Leonid
--
Leonid Gibiansky, Ph.D.
Pres
should allow (in theory, given sufficient amount of data) to recover the
true model, including the true error model. Log-transformation is just
the trick that allows to implement the exponential error model in nonmem.
Thanks
Leonid
------
Leonid Gibiansky, Ph.D.
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
nele.pl...@nycomed.com wrote:
Dear all,
I am trying to fit a PK model to oral data. In the data, we observed two
things: First, CL seems to be
ation than other model diagnostics)
Thanks
Leonid
------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Mats Karlsson wrote:
Dear Satyendra,
Interesting question. I d
arm)? Is it always stable (or at least as stable as
BLOCK(2))?
Thanks
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Mats Karlsson wrote:
Hi Steve,
For a
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Mats Karlsson wrote:
Hi Leonid,
Pls see below.
Mats Karlsson, PhD
Professor of Pharmacometrics
Dept of Pharmaceutical
probability of observing the value as extreme as the final-model
parameter estimates based on the bootstrap distribution (using a percent
of bootstrap estimates that are below or above the final-model. estimate).
Thanks
Leonid
--
Leonid Gibiansky, Ph.D
(although I never tried it)
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Elassaiss - Schaap, J. (Jeroen) wrote:
Thomas,
Two solutions (their smart
I would try
IF(W.LE.0.01) W = 1
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
hoxu8...@mail.usyd.edu.au wrote:
Dear Nonmem users,
I have been
SUM=1+ EXP(THETA(1)+ETA(1)) + EXP(THETA(2)+ETA(2))
F1=EXP(THETA(1)+ETA(1))/SUM
F2=EXP(THETA(2)+ETA(2))/SUM
F3=1/SUM
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
Anubha
You do not have time=0 records, therefore, A(1)=0
Try
HZ=BASE*TIME
(and use $PRED rather than $PK)
Leonid
--
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web:www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel:(301) 767 5566
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
1 - 100 of 394 matches
Mail list logo