RE: Bayesian estimates of multiple occasions

From: [email protected] [mailto:[email protected]] On Behalf Of markus joerger Sent: Thursday, June 03, 2010 8:20 AM To: [email protected] Subject: [NMusers] Bayesian estimates of multiple occasions dear NONMEM community, I'd like to estimate the potential value of individual dose adaptations of an anticancer drug by applying Bayesian POSTHOC (individual) estimates on a previous model. As I have data on the interoccasion variability, I put "OCC" into the table for the Bayesian run, but NONMEM seems not to accept two occasions for POSTHOC-only: ""0DATA REC 31: TIME DATA ITEM IS LESS THAN PREVIOUS TIME DATA ITEM 0DATA REC 51: TIME DATA ITEM IS LESS THAN PREVIOUS TIME DATA ITEM"" I'd guess that >1 occasion should also work with POSTHOC-only, with an adequate input of IOV and residual variability. Otherwise, it might be necessary to code two time-separate dosing events within one time-scale? Can anybody explain? thanks and kind regards, Markus my table looks like that: ---------------------------------------------------------------------------- ------------------- C, ID, OCC, TIME, AMT, RATE, DV, CMT, MDV, EVID, AGE, BILI, BSA, SEX -- Markus Joerger MD PhD Department of Medical Oncology Rorschacherstr. 95 9007 St. Gallen Switzerland [email protected] [email protected] phone: +41-765591070 fax: +41-714946368