This does leave out the ability to model a power term, theta(2). Fortunately, if there are fewer than 4 thetas that are not mu-referenced, usually the EM algorithms can still solve the problem, but with less efficiency. The parameterization I recommend for this particular problem, and include the power term, is:
MU_1=THETA(1) CL=(CLCR/120)**THETA(2)*EXP(MU_1+ETA(1)) As Henrik states. The THETA(1) is at least MU referenced here. Also, linear MU referencing is preferred, even though this means having to deal with initial theta(1) and reported theta(1) as log of typical clearance. As of NONMEM 7.3, you can refer to THETA(1) in the original domain, while still linear MU referencing, by adding: $THETAI THETA(1)=LOG(THETAI(1)) $THETAR THETAR(1)=EXP(THETA(1)) Robert J. Bauer, Ph.D. Vice President, Pharmacometrics, R&D ICON Development Solutions 7740 Milestone Parkway Suite 150 Hanover, MD 21076 Tel: (215) 616-6428 Mob: (925) 286-0769 Email: [email protected]<mailto:[email protected]> Web: www.iconplc.com<http://www.iconplc.com/> From: [email protected] [mailto:[email protected]] On Behalf Of Henrik B. Nyberg Sent: Monday, April 14, 2014 8:49 AM To: Ayyappa Chaturvedula; [email protected] Subject: [NMusers] RE: Mu referencing in covariate model Dear Ayyappa, It is my understanding that you can apply your time-varying covariates on the individual level instead of the typical value. Something like this: CL=(CLCR/120)*EXP(MU_1+ETA(1)) Your MU_1 will then represent a typical clearance dependent on CLCR instead of just a typical clearance, but the mu referencing should go through. Best regards Henrik B. Nyberg From: [email protected]<mailto:[email protected]> [mailto:[email protected]] On Behalf Of Ayyappa Chaturvedula Sent: 09 April 2014 02:21 To: [email protected]<mailto:[email protected]> Subject: [NMusers] Mu referencing in covariate model Dear Group, I want to test CRCL as a covariate on clearance as follows: TVCL = THETA(1)*(CLCR/120)**THETA(2). I am using EM methods for estimation and the following code can be used as per the manual: MU_1= LOG(THETA(1))+THETA(6)*LOG(CLCR/120) CL=EXP(MU_1+ETA(1)) The issue with this code for my dataset is that CLCR is not constant within individual with different observations and violates the mu-referencing rules. I appreciate your suggestions and help on this. Regards, Ayyappa -- LEGAL NOTICE This message is intended for the use of the named recipient(s) only and may contain confidential and / or privileged information. If you are not the intended recipient, please contact the sender and delete this message. Any unauthorised use of the information contained in this message is prohibited. Mango Business Solutions Limited is registered in England under No. 4560258 with its registered office at Suite 3, Middlesex House, Rutherford Close, Stevenage, Herts, SG1 2EF, UK. PLEASE CONSIDER THE ENVIRONMENT BEFORE PRINTING THIS EMAIL <br /><br /> ICON plc made the following annotations. ------------------------------------------------------------------------------ This e-mail transmission may contain confidential or legally privileged information that is intended only for the individual or entity named in the e-mail address. If you are not the intended recipient, you are hereby notified that any disclosure, copying, distribution, or reliance upon the contents of this e-mail is strictly prohibited. If you have received this e-mail transmission in error, please reply to the sender, so that ICON plc can arrange for proper delivery, and then please delete the message. Thank You, ICON plc South County Business Park Leopardstown Dublin 18 Ireland Registered number: 145835
