Dear Kyun, in the current I only have diagonal element usually I only used distribution of fixed-effects parameters to account for the uncertainty of this level (trial level), then for each sampled fixed-effects parameter, I would just use the estimated ETA to simulate patients within each trial. I never practice like you suggested, i.e. using the var-cov matrix to sample Omega/Sigma too and I realize that I don't have a strong rationale for opposing this approach so I wonder if others would share some insights into this
________________________________ From: "kyunseop....@gmail.com" <kyunseop....@gmail.com> To: Ethan Wu <ethan.w...@yahoo.com> Sent: Thursday, February 26, 2009 8:19:06 PM Subject: RE: [NMusers] var-cov matrix issue? Dear Ethan, If your model has only diagonal elements in OMEGA matrix, you don't need to care about the following - positive definiteness of OMEGA matrix during simulation. If you use VAR-COV output of NONMEM for the simulation, it means you generate THETAs, OMEGA matrix and SIGMA matrix from the MVN distribution of VAR-COV matrix. OMEGA and SIGMA matrix are always positive definite in nature. However, if you generate full-block OMEGA matrix using MVN (multi-variate normal) of VAR-COV matrix, many of generated OMEGA matrix will not be positive definite. One way to avoid this is test positive definiteness and discard in-adequate ones. This may help you. Regards, Kyun Seop Bae MD PhD ________________________________ From: Ethan Wu [mailto:ethan.w...@yahoo.com] Sent: Thursday, February 26, 2009 4:05 AM To: kyunseop....@gmail.com Cc: nmusers@globomaxnm.com Subject: Re: [NMusers] var-cov matrix issue? Dear Kyun, thanks for your help. I don't know if I understand this one "Some caution is necessary to simulate omega matrix that is alwasy positive definite. " Could you explain a bit more? ________________________________ From: "kyunseop....@gmail.com" <kyunseop....@gmail.com> To: Ethan Wu <ethan.w...@yahoo.com> Cc: nmusers@globomaxnm.com Sent: Tuesday, February 24, 2009 3:07:30 PM Subject: RE: [NMusers] var-cov matrix issue? Hi, Ethan, I think your question can be reduced whether pseudo-inverse matrix can be used instead of inverse matrix. I do not know quite different cases, but I suppose it can be used. To be more adequate answer in your context, MATRIX=R option could be more appropriate, if you use VAR-COV matrix output for simulation under normal distribution assumtion, If your data supports normal distribution assumption, MATRIX=R option will not give much difference in SEs. Default VAR-COV output in NONMEM is a kind of sandwich estimate, which is thought to be more robust (a little larger) than inverse Fisher's information matrix (given MATRIX=R option). Some caution is necessary to simulate omega matrix that is alwasy positive definite. This may help you. Thanks, Kyun Seop Bae MD PhD Email: kyunseop....@gmail.com ________________________________ From: owner-nmus...@globomaxnm.com [mailto:owner-nmus...@globomaxnm.com] On Behalf Of Ethan Wu Sent: Tuesday, February 24, 2009 11:09 AM To: justin.wilk...@novartis.com Cc: nmusers@globomaxnm.com Subject: Re: [NMusers] var-cov matrix issue? Hi Justin, only ETA was estimated with high SE but, again, I guess it came back to the question: how trustful it is if such error message appears ________________________________ From: "justin.wilk...@novartis.com" <justin.wilk...@novartis.com> To: ethan.w...@yahoo.com Sent: Tuesday, February 24, 2009 1:19:17 PM Subject: Fw: [NMusers] var-cov matrix issue? Dear Ethan, Algorithmically singular matrices are often a sign that that your model is ill-conditioned in some way; I would be careful in how I used the variance-covariance matrix in this scenario, and especially for simulation. Are there any parameters that are being estimated with particularly high standard errors? This might suggest overparamaterization. Not sure how helpful this is! Best Justin Justin Wilkins Senior Modeler Modeling & Simulation (Pharmacology) CHBS, WSJ-027.6.076 Novartis Pharma AG Lichtstrasse 35 CH-4056 Basel Switzerland Phone: +41 61 324 6549 Fax: +41 61 324 3039 Cell: +41 76 561 0949 Email : justin.wilk...@novartis.com <mailto:justin.wilk...@novartis.com> ----- Forwarded by Justin Wilkins/PH/Novartis on 2009/02/24 07:15 PM ----- Ethan Wu <ethan.w...@yahoo.com> Sent by: owner-nmus...@globomaxnm.com 2009/02/24 07:12 PM To nmusers@globomaxnm.com cc Subject [NMusers] var-cov matrix issue? Dear all, I recently encounter this error message (below). My objective was to use nonmem var-cov output for approximation of distribution of parameters for performing a simulation. if such error message occur, is the var-cov matrix still OK to use? -- I know that better way to figure out distribution of parameters is to do bootstrap, but given limited time I have..... thanks "0MINIMIZATION SUCCESSFUL NO. OF FUNCTION EVALUATIONS USED: 331 NO. OF SIG. DIGITS IN FINAL EST.: 3.3 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: 0.11E-02 SE: 0.23E-01 P VAL.: 0.96E+00 0S MATRIX ALGORITHMICALLY SINGULAR 0S MATRIX IS OUTPUT 0INVERSE COVARIANCE MATRIX SET TO RS*R, WHERE S* IS A PSEUDO INVERSE OF S 1 "
