Dear Waroonrat, That's almost a philosophical question! One could argue that the data simply do not provide this information and so there is no way to estimate IIV for V2 and Q. One could also argue that perhaps FOCE-I does not provide the most accurate approximation to the likelihood possible, and that you could perhaps get closer using SAEM or some other routine. I have always assumed that if FOCE-I cannot recover it, it is not there, but I have seen some things lately that make me believe this may not be the case. Try SAEM and see if that performs better :-).
Kind regards, Rik From: Waroonrat Sukarnjanaset [mailto:waroon...@hotmail.com] Sent: 28 June 2017 11:49 To: Rik Schoemaker <rik.schoema...@occams.com> Cc: nmusers@globomaxnm.com Subject: Re: [NMusers] Two compartment model with fixed omega parameters Dear Martin and Rik, Thank you so much for your helpful suggestions, I really appreciate it. Could you please recommend me which estimation methods would be the possible methods to estimate IIV for V2 and Q? Sincerely, Waroonrat ________________________________ From: Rik Schoemaker <rik.schoema...@occams.com<mailto:rik.schoema...@occams.com>> Sent: Tuesday, June 27, 2017 11:29 AM To: Waroonrat Sukarnjanaset Cc: nmusers@globomaxnm.com<mailto:nmusers@globomaxnm.com> Subject: RE: [NMusers] Two compartment model with fixed omega parameters Dear Waroonrat, I fully support Martin's suggestions below, but to come back to your original question: the fact that IIVs are set to zero for V2 and Q does not mean the second compartment is 'gone'. If you would examine your model predictions, inclusion of the second compartment -even without IIV- would result in the characteristic bend in the elimination phase of your compound when viewed on the log-scale. It is quite often that NONMEM FOCE-I cannot estimate IIV for V2 and Q and fixing them to zero can result in perfect predictions of your observed concentration profiles including the two-compartment behaviour. No-one would claim that these parameters are in fact the same for every single subject, just that the data cannot support making them different for your subjects in this case. Kind regards, Rik Schoemaker, PhD Occams Coƶperatie U.A. Malandolaan 10 1187 HE Amstelveen The Netherlands www.occams.com<http://www.occams.com> +31 20 441 6410 rik.schoema...@occams.com<mailto:rik.schoema...@occams.com> [cid:image001.png@01D2F008.8FFF8D20] From: owner-nmus...@globomaxnm.com<mailto:owner-nmus...@globomaxnm.com> [mailto:owner-nmus...@globomaxnm.com] On Behalf Of Martin Bergstrand Sent: 27 June 2017 11:30 To: Waroonrat Sukarnjanaset <waroon...@hotmail.com<mailto:waroon...@hotmail.com>> Cc: nmusers@globomaxnm.com<mailto:nmusers@globomaxnm.com> Subject: RE: [NMusers] Two compartment model with fixed omega parameters Dear Waroonrat, To know if a model "adequately describe the data" you need to study model diagnostics. Read more for example here: http://onlinelibrary.wiley.com/doi/10.1002/psp4.12161/full The AIC numbers in your case indicate that the two compartment model is a much better description of your data than the one compartment model (read on AIC here: https://en.wikipedia.org/wiki/Akaike_information_criterion). However, this is only a relative comparison and as pointed out before does not say anything about whether any of the models "adequately describe the data". All the best, Martin Bergstrand, Ph.D. Senior Consultant Pharmetheus AB From: owner-nmus...@globomaxnm.com<mailto:owner-nmus...@globomaxnm.com> [mailto:owner-nmus...@globomaxnm.com<mailto:owner-nmus...@globomaxnm.com>] On Behalf Of Waroonrat Sukarnjanaset Sent: Tuesday, June 27, 2017 10:52 AM To: nmusers@globomaxnm.com<mailto:nmusers@globomaxnm.com> Subject: [NMusers] Two compartment model with fixed omega parameters Dear NMusers, I have tried to find an appropriate base model. I found that two compartment model with fixed Omega of V2 and Omega of Q = 0 (AIC 1860.17) provided smaller AIC than one compartment model (AIC 1921.83) did. >From these findings (no variability on V2 and Q), is it suggesting that one >cpt model could adequately describe the data? I would truly appreciate it if you could give me some suggestions. Kind regards, Waroonrat