From: Wenhui Zhang
Subject: [NMusers] Time to event variable 
Date: Thu, 24 Aug 2006 11:30:57 -0500

Dear All

I am trying to model one of the adverse events we observed in animal studies as the time-to-event variable. 
All studies were multiple dose study. The difference is that in some of studies animals were moved
away from study after adverse event was observed, i.e animals were not rechallenged with compound
any more. In other studies, the animals were rechallenged with compound after adverse event was
observed. Could anybody shed a light on how to model the multiple hazards , i.e multiple doses, and
different data structure (with and with rechallenge)? Thanks a lot. 


From: Matthew Riggs
Subject: Re: [NMusers] Time to event variable
Date: Fri, 25 Aug 2006 05:55:28 -0700 (PDT)

Hi Wenhui,
There's an example that may help you by Cox and
Sheiner (Repeated measures time to event with
time-varying concentration and hazard) -
implementation information is available at:

Start with the 'readme' file and then the data
formatting & NONMEM control file examples are in the
"general_hazard" folder.

The literature reference is: Cox et al. A population
pharmacokinetic-pharmacodynamic analysis of repeated
measures time-to-event pharmacodynamic responses: the
antiemetic effect of ondansetron. J Pharmacokinet
Biopharm 1999; 27(6):625-44.

Hope this helps.

Matthew M. Riggs, Ph.D
Principal Scientist
Metrum Research Group LLC
2 Tunxis Road, Suite 112
Tariffville, CT 06081