RE: posthoc step
From: "Steve Duffull" sduffull@pharmacy.uq.edu.au
Subject: RE: [NMusers] posthoc step
Date: Wed, December 8, 2004 8:10 pm
Hi
To continue the story a little on Jerry's example.
I ran the model in WinBUGS - see code below.
model {
for (j in 1:3) {
data[j] ~ dnorm(model[j], tau)
model[j] <- 10*exp(-k*time[j])
}
k ~dnorm(10,20) # this is mean, precision where precision = 1/var
sigma2 <- 0.04
tau <- 1/(sigma2)
}
list(
time=c(1, 2, 3),
data=c(3.87, 1.66, 0.44)
) # data
list(
k=2) # initial estimate of k (I tried others with the same result)
When the prior variance was set to 4 Khat was estimated at 0.95
When the prior variance was set to 1 Khat was estimated at 0.96
When the prior variance was set to 0.1 Khat was estimated at 1.2
When the prior variance was set to 0.05 Khat was estimated at 10
These are similar to the NONMEM and SAS results when variance was 4. In addition,
there appeared to be a rapid change in Khat occurred with small changes in
variance (results not shown).
Steve
=========================================
Stephen Duffull
School of Pharmacy
University of Queensland
Brisbane 4072
Australia
Tel +61 7 3365 8808
Fax +61 7 3365 1688
University Provider Number: 00025B
Email: sduffull@pharmacy.uq.edu.au
www: http://www.uq.edu.au/pharmacy/sduffull/duffull.htm
PFIM: http://www.uq.edu.au/pharmacy/sduffull/pfim.htm
MCMC PK example: http://www.uq.edu.au/pharmacy/sduffull/MCMC_eg.htm