Due To Rounding Errors Error 134 Nonmem
I used log transformed data. But I kept getting Rounding Error message: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 0MINIMIZATION TERMINATED DUE TO ROUNDING ERRORS (ERROR=134) NO. OF FUNCTION EVALUATIONS USED: 958 NO. OF SIG. DIGITS UNREPORTABLE ETABAR IS THE ARITHMETIC MEAN OF THE ETA-ESTIMATES, AND THE P-VALUE IS GIVEN FOR THE NULL HYPOTHESIS THAT THE TRUE MEAN IS 0. ETABAR: 0.13E-01 -0.62E-02 0.66E-02 -0.39E-02 0.49E-01 0.44E-01 P VAL.: 0.86E+00 0.93E+00 0.94E+00 0.96E+00 0.74E+00 0.67E+00 1 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Could someone please shed some light on what is causing this error and what I should do to get rid of it? The model fit at the point of termination looks quite good, and the parameter estimates are quite good too. Thank you. Jeri Sottos ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ $PROBLEM 2Comp Parent Drug 1Comp Metabolite Model -- Log Transformed DV $DATA DATA_LOG.PRN $INPUT ID AMT RATE TIME DV CMT EVID $SUBROUTINES ADVAN6 TRANS1 TOL=5 $MODEL NPAR=6 NCOMP=3 COMP=(PARCEN DEFDOSE DEFOBS) ;CENTRAL COMPARTMENT FOR PARENT DRUG COMP=(PARPER NODOSE) ;PERIPHERAL COMPARTMENT FOR PARENT DRUG COMP=(METCEN NODOSE) ;CENTRAL COMPARTMENT FOR METABOLITE $PK CLt=THETA(1)*EXP(ETA(1)) ;PARENT DRUG CENTRAL CLEARANCE Vc=THETA(2)*EXP(ETA(2)) ;PARENT DRUG CENTRAL COMPARTMENT VOLUME CLd=THETA(3)*EXP(ETA(3)) ;PARENT DRUG DISTRIBUTION CLEARANCE Vp=THETA(4)*EXP(ETA(4)) ;PARENT DRUG PERIPHERAL COMPARTMENT VOLUME CLtm=THETA(5)*EXP(ETA(5)) ;METABOLITE CENTRAL CLEARANCE Vcm=THETA(6)*EXP(ETA(6)) ;METABOLITE CENTRAL COMPARTMENT VOLUME S1=Vc/1000 S3=Vcm/1000 $DES DADT(1)=-(CLt+CLd)/Vc*A(1)+CLd/Vp*A(2) DADT(2)=CLd/Vc*A(1)-CLd/Vp*A(2) DADT(3)=-CLtm/Vcm*A(3)+.4045*CLt/Vc*A(1) ;40.45% OF PARENT DRUG IS COVERTED INTO METABOLITE $ERROR FLAG=0 IF(AMT.NE.0)FLAG=1 ;dosing records only IPRED=LOG(F+FLAG) ;transform the prediction to the log of the ;prediction ; IPRED=log(f) for concentration records and ; IPRED=log(f+1) for dose records R1=0 IF (CMT.EQ.1) R1=1 R2=0 IF (CMT.EQ.3) R2=1 Y1=IPRED+EPS(1) Y3=IPRED+EPS(2) Y=R1*Y1+R2*Y3 YORI=EXP(Y) ; y in normal scale DVORI=EXP(DV) ; DV in normal scale IRES=EXP(DV)-EXP(IPRED) $THETA (10,33) (10,27) (30,60) (30,86) (10,17) (10,36) $OMEGA BLOCK(6) .24 .01 .28 .27 .01 .36 .20 .16 .25 .32 .24 .05 .24 .10 0.77 .17 .03 .09 .02 0.43 0.47 $SIGMA BLOCK (2) .06 .09 .18 $ESTIMATION METHOD=1 INTERACTION PRINT=10 POSTHOC REPEAT MAXEVAL=9999 $TABLE ID TIME CMT IPRED IRES CLt Vc CLd Vp CLtm Vcm NOPRINT FILE=mTBL.TXT $COV $SCAT DVORI VS TIME BY CMT $SCAT YORI VS TIME BY CMT $SCAT IRES VS TIME BY CMT ^^^^^^^
only measure the parent compound concentration which was far below the dose. For example, 120 umol was given as i.v infusion for 1 h but the plasma concentration of the parent compound is only around 0.02-1.5 uM. I just tried the simple ADVAN3 TRANS4 as follows, however, the result turns out to be a very large V2 and very small CL and keeping giving the rounding error ( error=134)! Does anyone can help me figure it out? $PK V1=THETA(1)*EXP(ETA(1)) V2=THETA(2)*EXP(ETA(2)) CL=THETA(3)*EXP(ETA(3)) Q=THETA(4)*EXP(ETA(4)) K=CL/V1 K12=Q/V1 K21=Q/V2 S1=V1 $ERROR IPRED=F W=F IRES=DV-IPRED IWRES=IRES/W Y= IPRED+W*EPS(1) http://www.cognigencorp.com/nonmem/nm/98may132003.html $OMEGA 0.25 $OMEGA 0.5 $OMEGA 0.5 $OMEGA 0.5 $SIGMA 0.25 Thanks a lot. Ping _______________________________________________________ From: Nick Holford n.holford@auckland.ac.nz Subject: Re: [NMusers] Help on rounding error ( error=134) ! Date: Mon, 13 Nov 2006 11:50:39 +1300 Ping, Did you look at the model predictions? If the predictions look Ok then you can ignore the rounding error message. A visual predictive check would be a good way to http://www.cognigencorp.com/nonmem/nm/99nov122006.html decide if your model predictions are OK. You say CL is small and V2 is large. On what basis of prior knowledge do you judge them to be small and large? Unless you have some good reason e.g. CL much bigger than cardiac output then it isn't usually helpful to judge the numerical values to be small or large. Nick -- Nick Holford, Dept Pharmacology & Clinical Pharmacology University of Auckland, 85 Park Rd, Private Bag 92019, Auckland, New Zealand email:n.holford@auckland.ac.nz tel:+64(9)373-7599x86730 fax:373-7556 http://www.health.auckland.ac.nz/pharmacology/staff/nholford/ _______________________________________________________ From: "Toufigh Gordi" tgordi@Depomedinc.com Subject: Re: [NMusers] Help on rounding error ( error=134) ! Date: Sun, 12 Nov 2006 20:19:14 -0800 Hi Ping, I am guessing that you have looked at some graphs of your data and can clearly see a bi-phasic decline, or have some prior knowledge about the drug, and that's why you apply a 2-comp model. I would suggest that early on in the model-building, you start with one ETA (my suggestion would be CL or VC). If you find a model that does a relatively good job, you can start adding ETAs to see whether they improve the fit. I don't knwo about the NONMEM codes for various
is quite unreliable when it comes to helping me to decide if it has converged in a consistent and meaningful way." NONMEM is consistent in giving the same unhelpful information about https://www.mail-archive.com/nmusers@globomaxnm.com/msg00453.html whether it believes it can claim convergence i.e. with exactly the same compiler+options, CPU, http://www.nonlin-model.org/fiche.php?id=42&PHPSESSID=f48e6c9dfada8dadf4ac8d9f26273932 NONMEM patch level it gives the same numbers (change any of these and of course you are quite likely to get something different). But it is inconsistent in the real world sense of giving me a solid feeling that it really converged in a way that gives me some confidence in the results. I have cited due to investigations that show one cannot have this kind of confidence because the parameter estimate distribution is equivalent whether or not NONMEM claims to have not converged (e.g. due to rounding errors), converged but no $COV or converged with $COV. So I ask for SIGDIG=6 and ignore NONMEM's reported convergence status. I typically get more than 3 sig digs on the runs that interest me and often more than 6 and due to rounding once in a while $COV is successful. But I use other criteria to judge suitability of the model - esp simulation based checks because these are in the spirit of what I really want to use the model for. Standard errors are just part of a historical description of a model with no practical relevance to predictive checks. Real world application of modelling implicitly or explicitly requires a prediction from the model. Yes -- Like you I like to see the run converge and %COV complete but I also like to see the sun shine every day. If it doesnt shine my life goes on... (its raining today in Auckland). NONMEMs termination messages are as reliable as the weather in this part of the world. Nick Mark Sale - Next Level Solutions wrote: > > Nick, > I'm interested in exactly what you mean by "unreliable". Is it > sensitivity/specificity for a "bad" model? I suspect that we all would > prefer if our models converge and have a successful covariance step. And so > (I think), models that pass these tests are "better" models than those that > don't (everything else being equal). But, if we are unable to find a model > that passes these test
temps (TIME) la date (DATE) l'identification des individus (ID) les doses administrées (AMT) le débit d'une perfusion (RATE) la variable dépendante (DV) la nature de l'information de la ligne (MDV) la nature de l'information de la ligne, en plus élaboré (EVID) les covariables (WT, SEX, AGE,...) un éventuel état d'équilibre (SS) Intervalle de dose (II) le compartiment (CMT) Doses additionnelles (ADDL) Généralités sur les base de données avec nonmem resultats Fichiers résultats Final Parameter Estimate Fonction Objective (OF) Gradients evaluation Condition number Items de diagnostic (PRED, CPRED, EPRED...) Tutorial DATA Checking Choix d'un modèle de base Critères d'évaluation d'un modèle de Base Analyse des posthoc Covariables Classement des analyses intermédiaires Modèle complet Elimination des covariables inutiles Choix d'un modèle final Evaluation d'un modèle Exemples PK 1 compartiment, bolus intra-veineux PK 2 compartiments, bolus intra-veineux PK 3 compartiments, bolus intra-veineux PK 1 compartiment, perfusion, covariables PK 1 compartiment, voie orale PK 2 compartiments, voie orale PK 3 compartiments, voie orale PK 1 compartiments, voie orale, équations différentielles Simulation PK 1 cpt, perfusion Modélisation du Temps Après la Dose (TAD) Modélisation d'une Baseline (BSE) Tips modélisation du Temps Après la Dose (TAD) modélisation d'une baseline (BSE) Wings for nonmem Contraindre un THETA Obliger un THETA à être inferieur à un autre Donnée Manquante (var. indép.) MU referencing Docu Livres Article NSK R tips readline with R studio Table Références index Gradients Les gradients servent au calcul de la fonction objective. A chaque paramètre calculé (THETA, OMEGA et SIGMA) correspond un gradient. Quand un THETA a une valeur fixe, il n'existe donc pas de gradient pour cette valeur non calculée. Quand l'analyse s'est normalement terminée (MINIMIZATION SUCCESSFUL) les gradients sont tous petits, inférieurs à 1. Quand l'analyse s'est arrêtée prématurement, souvent au moins un des gradients à une valeur élevée. L'estimation correspondante est souvent à modifier. e.g. MINIMIZATION TERMINATED DUE TO ROUNDING ERRORS (ERROR=134) No. OF FUNCTION EVALUATIONS USED: 899 No. OF SIG. DIGITS IN FINAL EST.: 1.6 Problème Cette erreur correspond à une insuffisance de digits significatifs, ici 1.6. Dans le fichier Input, bloc $ESTIMATION, l'option NSIGT=3 est peut-etre spécifiée. Dans notre exemple, le nombre de digits s