NONMEM Users Network Archive

Hosted by Cognigen

RE: $COV UNCONDITIONAL PRINT=E

From: Bauer, Robert <Robert.Bauer>
Date: Mon, 26 Oct 2009 12:31:16 -0400

Sam:
The nature of the $COV step using classical NONMEM methods is it can
take longer than the $EST command at times. There is no infinite loop,
it just has to evaluate OBJ often in cases of large problems. The SIGL
does not help with this, and the ctrl-K and ctrl-E switches do not act
during evaluation of the $COV STEP. advan13 is best used for the Monte
Carlo methods. If you are not particular about getting $COV results by
classical NONMEM methods, you can ctrl-C.
 
Regarding BAYES analysis, the release notes, and the slides I gave at
the workshops (make stable programs section of slides), inform the user
that Monte Carlo methods can call the user model with very extreme
values. Thus, insert protective code, the kind that avoid square
rooting negative numbers, exponentiating very large numbers, etc.
For new methods, use INTERACTION, even when error is homoscedastic.
 
 

Robert J. Bauer, Ph.D.
Vice President, Pharmacometrics
ICON Development Solutions

Tel: (215) 616-6428
Mob: (925) 286-0769
Email: Robert.Bauer
Web: www.icondevsolutions.com

 

 

 

________________________________

From: owner-nmusers
On Behalf Of Sam Liao
Sent: Monday, October 26, 2009 11:36 AM
To: nonmem
Subject: [NMusers] $COV UNCONDITIONAL PRINT=E



Dear NONMEM team:

I have two nm7 questions.

 

I have a PKPD model using ADVAN13 to solve the ODE. It took 12 hours to
complete the $EST step with rounding error.

But it's been over 15 hours running the $COV step with UNCONDITIONAL
option.

 

This is much longer time than I expected. Could this be an infinitive
loop? Should I interrupt the run and try smaller SIGL in $COV? I
tried the CTL-K or CTL-E to exit, but it did not work for me.

 

The second question related to BAYES method in $EST step. The model run
successfully using FOCE method. But when I tried the BAYES method with
NOABORT option, it terminated with 'OBJECTIVE FUNCTION IS INFINITE' in
Burn-in mode after 10 iterations. The statement used as below. How can
I get around this problem?

=======================

$SUBROUTINES ADVAN13 TOL=6


$EST METHOD=BAYES NBURN=100 NSAMPLE=3000 SIGL=6 NOABORT =
FILE=RUN136.TXT

 

Best regards,

Sam

 

From: owner-nmusers
On Behalf Of Bauer, Robert
Sent: Sunday, October 25, 2009 11:29 PM
To: nonmem
Subject: RE: [NMusers] method=ITS, OPTIMIZATION NOT TESTED (?!)

 

Pavel:

The objective function progress looks good. You should expect some
Monte Carlo fluctuations. You should also run more iterations (perhaps
NITER=200), and set CTYPE=3, which turns on the termination tester. =
To
resume where you left off, rename your new control stream file, and put
in the following lines.

 

$EST METHOD=CHAIN NSAMPLE=0 ISAMPLE=50
FILE=my_old_control_stream_file.ext

$EST METHOD=IMP NITER=200 CTYPE=3 =
FILE=my_new_control_stream_file.ext

 

Make sure you are linear MU referencing to get the greatest efficiency.

 

 

Robert J. Bauer, Ph.D.
Vice President, Pharmacometrics
ICON Development Solutions

Tel: (215) 616-6428
Mob: (925) 286-0769
Email: Robert.Bauer
Web: www.icondevsolutions.com

 

 

 

 

________________________________

From: owner-nmusers
On Behalf Of nonmem
Sent: Saturday, October 24, 2009 8:03 PM
To: nmusers
Subject: [NMusers] method=ITS, OPTIMIZATION NOT TESTED (?!)

Hello NONMEM Team,

I found method=imp useful when there are local maxima. Nevertheless, =
at
the end of optimization it prints a message, which makes me feel
somewhat uncomfortable: OPTIMIZATION NOT TESTED. Also, the final
objective function is not always the lowest one. An example is below.
How do we interpret the results in this case?

 THETAS THAT ARE SIGMA-LIKE:
 MONITORING OF SEARCH:

 iteration 0 OBJ= 10625.663135214874
 iteration 1 OBJ= 10601.188754983375
 iteration 2 OBJ= 10537.895114114934
 iteration 3 OBJ= 10471.674625518765
 iteration 4 OBJ= 10430.297437731866
 iteration 5 OBJ= 10461.973668565577
 iteration 6 OBJ= 10462.638834406265
 iteration 7 OBJ= 10423.464983371641
 iteration 8 OBJ= 10417.959956991735
 iteration 9 OBJ= 10417.594007447198
 iteration 10 OBJ= 10414.708468642830
 iteration 11 OBJ= 10427.810693855947
 iteration 12 OBJ= 10412.889081059604
 iteration 13 OBJ= 10411.980622268416
 iteration 14 OBJ= 10424.501127174915
 iteration 15 OBJ= 10416.332869468861
 iteration 16 OBJ= 10416.622580251338
 iteration 17 OBJ= 10412.401585537709
 iteration 18 OBJ= 10415.117257355550
 iteration 19 OBJ= 10415.302370961055
 iteration 20 OBJ= 10409.066188189252
 iteration 21 OBJ= 10413.780620468329
 iteration 22 OBJ= 10410.787496174480
 iteration 23 OBJ= 10410.633582415931
 iteration 24 OBJ= 10409.970257443048
 iteration 25 OBJ= 10409.702420124611
 iteration 26 OBJ= 10409.213115058612
 iteration 27 OBJ= 10409.690639357370
 iteration 28 OBJ= 10410.016047785200
 iteration 29 OBJ= 10408.157468814226
 iteration 30 OBJ= 10407.779614704938
 iteration 31 OBJ= 10410.164563157052
 iteration 32 OBJ= 10408.364552302961
 iteration 33 OBJ= 10407.431920727997
 iteration 34 OBJ= 10408.286189641487
 iteration 35 OBJ= 10407.907347050501
 iteration 36 OBJ= 10407.451608770069
 iteration 37 OBJ= 10407.189482360372
 iteration 38 OBJ= 10406.484357336147
 iteration 39 OBJ= 10409.167125968375
 iteration 40 OBJ= 10406.840873883246
 iteration 41 OBJ= 10407.679485561714
 iteration 42 OBJ= 10405.341101045238
 iteration 43 OBJ= 10404.704382334516
 iteration 44 OBJ= 10405.348023082915
 iteration 45 OBJ= 10405.347406984720
 iteration 46 OBJ= 10401.873473651774
 iteration 47 OBJ= 10404.036204419035
 iteration 48 OBJ= 10405.072916975221
 iteration 49 OBJ= 10402.976628923887
 Elapsed estimation time in seconds: 30420.73
 iteration 50 OBJ= 10403.285958168881

 #TERM:
 OPTIMIZATION NOT TESTED

Thanks,

Pavel

 

 

 

 

ICON plc made the following annotations.
------------------------------------------------------------------------
------
This e-mail transmission may contain confidential or legally privileged
information
that is intended only for the individual or entity named in the e-mail
address. If you
are not the intended recipient, you are hereby notified that any
disclosure, copying,
distribution, or reliance upon the contents of this e-mail is strictly
prohibited. If
you have received this e-mail transmission in error, please reply to the
sender, so that
ICON plc can arrange for proper delivery, and then please delete the
message.
Thank You,
ICON plc
South County Business Park
Leopardstown
Dublin 18
Ireland
Registered number: 145835
 

ICON plc made the following annotations.
-------------------------------------------------------------------------=
-----
This e-mail transmission may contain confidential or legally privileged i=
nformation
that is intended only for the individual or entity named in the e-mail ad=
dress. If you
are not the intended recipient, you are hereby notified that any disclosu=
re, copying,
distribution, or reliance upon the contents of this e-mail is strictly pr=
ohibited. If
you have received this e-mail transmission in error, please reply to the =
sender, so that
ICON plc can arrange for proper delivery, and then please delete the mess=
age.
Thank You,
ICON plc
South County Business Park
Leopardstown
Dublin 18
Ireland
Registered number: 145835

Received on Mon Oct 26 2009 - 12:31:16 EDT

The NONMEM Users Network is maintained by ICON plc. Requests to subscribe to the network should be sent to: nmusers-request@iconplc.com.

Once subscribed, you may contribute to the discussion by emailing: nmusers@globomaxnm.com.