NONMEM Users Network Archive

Hosted by Cognigen

Re: Additive residual error

From: Denney, William S. <William.S.Denney>
Date: Tue, 12 Feb 2013 01:02:48 +0000

Hi Siwei,

In a similar situation previously, I've found fixing the additive error to =
a small value (~= 0.0001*LOQ) has provided a work-around for this. It us=
ually arises from a zero measurement needing to be nonzero for estimation p=
urposes. A better fix is to use the M2 method which should lower the const=
raint of needing additive error.

Thanks,

Bill

On Feb 11, 2013, at 7:27 PM, "siwei Dai" <ellen.siweidai

> Hi, NM users:
>
> I have a typical 2-compartment model that can describe my data quite well=
, except the final gradient for the additive residual error is '0'. I there=
fore fix the additive residual error to '0', but then NM would not run. I t=
ried different initial estimations for other parameters but the additive re=
sidual error seems to be the one that decide whether NM will run. Can anyon=
e tell me why this would happen and how to solve it?
>
> Thank you very much in advance for your help.
>
> Siwei
Received on Mon Feb 11 2013 - 20:02:48 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.