Re: Simulation with uncertainty + estimation

From: Marc Gastonguay Date: April 08, 2010 technical Source: mail-archive.com
Matts, You should be cautious about implementing this example as you've parameterized the model. There is an inconsistency between your model parameterization and the multivariate-normal assumption made when you use the var-cov matrix of the estimates to incorporate parameter uncertainty. See earlier discussions on this topic: http://www.cognigencorp.com/nonmem/current/2009-July/1816.html Marc
Quoted reply history
On Apr 8, 2010, at 4:20 AM, Kågedal, Matts wrote: > > Hi all, > A model for simulation with uncertainty was previously posted by Mats > Karlsson in this forum. > After a few bug fixes (with help from Mats) it now actually works. See below: > Matts Kågedal > AstraZeneca > > $PROB > $DATA data1.csv IGNORE=@ > $INPUT ID DV TIME XVCL XVV AMT > > ;data1= > ; 1 0 0 0 0 100 > ; 1 0 1 0 0 0 > ; 1 0 21 0 0 0 > ; 2 0 0 0 0 100 > ; etc > $SIM (20090726 NEW) SUBPROBLEMS=30 ; > $THETA ; estimates of THETA and OMEGA from previous run > (0,1) ; POP_CL theta1 > (0,10) ; POP_V theta2 > $OMEGA > 0.01 ; PPV_CL eta1 > 0.01 ; PPV_V eta2 > ;variance-covariance matrix of the THETA estimates from previous run > $OMEGA BLOCK(2) > 0.02 ; UNC_POP_CL eta3 > 0.0001 0.2 FIX; UNC_POP_V eta 4 > > $SIGMA .001 > $SUB ADVAN1 > $PK > CL=THETA(1)*EXP(ETA(1)) ; > V=THETA(2)*EXP(ETA(2)) ; > ;S1=V > TCLE=THETA(1); estimated typical value > TVE=THETA(2); estimated typical value > > IF (ICALL.EQ.4.AND.NEWIND.EQ.0) THEN ; do this just once per > subproblem > DO WHILE (ETA(3).LT.-.99.OR.ETA(4).LT.-9.9) CALL SIMETA(ETA) ;resample if > "bad" values > END DO > TVCL=THETA(1)+ETA(3) > TVV =THETA(2)+ETA(4) > > WRITE (53,*) TVCL, TVV ; Output simulated THETAs to file > ENDIF > > IF (ICALL.EQ.4) THEN ; do this for all simulated values > CL=TVCL*EXP(ETA(1)) ; with uncertainty for CL > V =TVV*EXP(ETA(2)) ; with uncertainty for V > ENDIF > > S1=V > K=CL/V > > $ERROR > Y =F*EXP(EPS(1)) > $INFN > IF (NEWIND.EQ.0) THEN > WRITE (52,*) THETA ; Output estimated THETAs to file > ENDIF > $EST MAX=9999 METH=1 INTER > > > > > Confidentiality Notice: This message is private and may contain confidential > and proprietary information. If you have received this message in error, > please notify us and remove it from your system and note that you must not > copy, distribute or take any action in reliance on it. Any unauthorized use > or disclosure of the contents of this message is not permitted and may be > unlawful. > > > > > > > > > > > > > > > > >
Apr 08, 2010 Matts Kågedal Simulation with uncertainty + estimation
Apr 08, 2010 Marc Gastonguay Re: Simulation with uncertainty + estimation