NONMEM Users Network Archive

Hosted by Cognigen

help on diagnostic of a problem -- about M3 method for LLOQ:

From: Ethan Wu <ethan.wu75>
Date: Thu, 11 Feb 2010 07:52:50 -0800 (PST)

Dear users,    I am working on a dataset with not small percentage be=
low LLOQ.   when I implemented M3 method to account for this, I always =
getting this error message: 0PROGRAM TERMINATED BY OBJ ERROR IN CLIK WI=
TH INDIVIDUAL 2 ID=0.19000000E+02 CONDITIONAL LIKELIHOOD FOR SOME OBSER=
VATION ESTIMATED TO BE NEGLIGIBLE   note that ID 19 is the first subj=
ect in the dataset. this is how I specify the $ERR (a combinative erro) a=
nd $EST: __________ $ERROR          IPRED = F =
   IRES  = DV-IPRED    FLAG=1    IF(STDY.GT.3) FLAG=
=0    DEL=0    W     = SQRT(THETA(7)**2*FLAG+THET=
A(8)**2*(1-FLAG)+THETA(9)**2*IPRED**2)    IF(W.EQ.0)DEL=1    =
IWRES = IRES/(W+DEL) IF (TYPE.EQ.2.AND.CMT.EQ.2) DUM=(LOQ-IPRED)/(THE=
TA(7)**2*FLAG+THETA(8)**2*(1-FLAG)+THETA(9)**2*IPRED**2)  CUMD=PHI(DU=
M) IF (TYPE.EQ.2) THEN  F_FLAG=1 Y=CUMD ENDIF IF (TYPE.EQ=
.1) THEN F_FLAG=0  Y = IPRED+W*EPS(1)  ENDIF $ESTIMATION M=
ETHOD=1 LAPLACIAN  MAXEVAL=9999 PRINT=10 NOABORT or this: $EST=
IMATION METHOD=1 INT LAPLACIAN  MAXEVAL=9999 PRINT=10 NOABORT =
_____ Interstingly, when I use Log-transformed data, the model would r=
un fine. this is how I specify $ERR (an additive error) and $EST, all the=
 other aspects of model are the same between two tries. Could someone hel=
p me understand what is happening? Thanks. _____ $ERROR    DEL =
  = 0    IF(F.LE.0) DEL = 1    IPRED = LOG(F+DEL)  =
  IRES  = DV-IPRED    FLAG=1    IF(STDY.GT.3) FLAG=0=

   DEL1=0    IF(W.EQ.0)DEL1=1    IWRES = IRES/(W+DEL1=
) IF (TYPE.EQ.2.AND.CMT.EQ.2) DUM  = (LOG(LOQ)-IPRED)/(THETA(7)*FLAG+=
THETA(8)*(1-FLAG))  CUMD=PHI(DUM) IF (TYPE.EQ.2) THEN  F_FLAG=
=1 Y=CUMD ENDIF IF (TYPE.EQ.1) THEN F_FLAG=0 Y=IPRED +E=
PS(1)*W ENDIF  $ESTIMATION METHOD=1 LAPLACIAN MAXEVAL=9999 PRIN=
T=10 NOABORT
Received on Thu Feb 11 2010 - 10:52:50 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.