NONMEM Users Network Archive

Hosted by Cognigen

Re: Betr.: Re: simulation question

From: Ethan Wu <ethan.wu75>
Date: Fri, 6 Feb 2009 05:28:04 -0800 (PST)

Hi Robm   the simulatio step runs fine as I checked by using SIMONLY=

 WITH INDIVIDUAL 16 ID=0.16000000E+02 NUMERICAL HESSIAN OF OBJ. FUNC. F=
OR COMPUTING CONDITIONAL ESTIMATE IS NON POSITIVE DEFINITE MESSAGE ISSU=
ED FROM ESTIMATION STEP AT 0TH ITERATION, UPON EVALUATION OF GRADIENT WIT=
H RESPECT TO OMEGA 0TRY SUBSTANTIALLY INCREASING "INITIAL ESTIMATE OF SIG=
MA" OR DECREASING "INITIAL ESTIMATE OF OMEGA"" ____________=
____________________ From: Rob ter Heine <Rob.terHeine
ers
:54:33 AM Subject: Betr.: Re: [NMusers] simulation question Dear Eth=
an, Have you tried removing the $ESTIMATION step and replace all value=
s with your final estimations? What does your result file say after termina=
tion? Sincerely Rob >>> Sebastian Ueckert <sebastian.uecke=
rt
PM, Ethan Wu <ethan.wu75
rying to compare several specific PK/PD study designs by: >  -- run 200=
 simulations with the final model (develope from original > dataset) >=
  -- fit the final model to the 200 simulated dataset > To achieve abov=
e, I used $SIM SUBPROB=200 option >  however, nonmem would  complet=
ely stop after running > into estimation problem at one specific simulati=
on/estimation cycles, for > some designs it stop even before 10th iterati=
ons. > Is there anyway nonmem could continue go on? > Or, does someone =
know alternative way to achieve the goal? > thanks > > > =
    
Received on Fri Feb 06 2009 - 08:28:04 EST

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.