Navin, There are several approaches but perhaps the simplest would be to create a NONMEM data file for one patient with the time points you want to use for the simulation. Then use NONMEM to simulate with 5000 sub-problems. This will create a table file with 5000 simulated patients. Each patient will have their own separate table in the table file e.g.
$SIMULATION (123456) ONLYSIM NSUB=5000 $TABLE ID TIME DV NOAPPEND ONEHEADER NOPRINT FILE=sim.tab However, if you also want to simulate the consequences of having different covariates in each patient then you will need to include simulation code for the covariate values so that each sub-problem uses different covariates. The difficulty of simulating covariates varies from easy to very hard depending on the number and type of covariates. An easy example would be to simulate age and weight e.g. $INPUT ID TIME WT AGE etc $THETA 70 ; popwt $THETA 60 ; popage $OMEGA BLOCK(2) 0.09 ; bsvwt -0.01 0.09 ; bsvage $PK IF (ICALL.EQ.4) THEN WT=THETA(1)*EXP(ETA(1)) AGE=THETA(2)*EXP(ETA(2)) ENDIF Finally you will have to put some thought into what you want to do with the simulated concentration predictions and how you will process them. Nick navin goyal wrote: > > Hello everybody, > I am trying to simulate PKPD data for 5000 patients, with each patient having > around 100 time points. > How could I create a data file for this simulation?? > Any help is appreciated. > Thanks > > Navin -- Nick Holford, Dept Pharmacology & Clinical Pharmacology University of Auckland, 85 Park Rd, Private Bag 92019, Auckland, New Zealand email:[EMAIL PROTECTED] tel:+64(9)373-7599x86730 fax:373-7556 http://www.health.auckland.ac.nz/pharmacology/staff/nholford/
