NONMEM Users Network Archive

Hosted by Cognigen

EVID=2 and RSE

From: Ahmed Suleiman <ahmed.suleiman>
Date: Wed, 13 Feb 2013 09:21:17 +0000

Dear NM Users,

I have a question regarding EVID=2 and the covariance step. I am fitting =
a tumor growth inhibition model to my data and I am still at the beginning =
where I am using a base model (no covariates). I have time changing covaria=
tes in the dataset which I am working with, some of which were measured at =
time points which do not coincide with the DV observations and hence I used=
 EVID=2.

When I first run the model (FOCE+I), I got very high relative standard erro=
rs for the parameter estimates. However when I duplicated the control strea=
m with just one change : IGNORE=(EVID.EQ.2), I got exactly the same OFV a=
nd the same parameter estimates (this is obvious since I have not included =
any of the covariates), but with dramatically lower relative standard error=
s.

Do you have an explanation for what may have went wrong ?
(by the way, I used FO just for testing and in both cases the RSEs were exa=
ctly the same).

Best Regards,

Ahmed Abbas Suleiman, MSc
PhD Candidate at Bonn University
Institute of Pharmacology - Clinical Pharmacology Unit
Hospital of the University of Cologne
Gleueler Str. 24, 50931 Cologne,
Germany
Phone: +49-(0)-221-478-3402

Received on Wed Feb 13 2013 - 04:21:17 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.