RE: posthoc step
From: "Steve Duffull" sduffull@pharmacy.uq.edu.au
Subject: RE: [NMusers] posthoc step
Date: Wed, December 15, 2004 5:43 am
Nick
> Let me ask the question more specifically -- if you used the same initial estimate
for K that was used for NONMEM, SAS, Excel Solver i.e. 10, and fixed the residual
error SD to 0.2 (no uncertainty!) with a prior on K of 10 and SD for the prior of
2 then what final estimate did you obtain? Did you get a number closer to 10 or
closer to 1?
For the problem you describe above - I started 5 chains with initial estimates of K0
= 1, 5, 10, 20 & 50 and generated 1000 samples from the posterior distribution for
each chain. The mean of the posterior distribution of each chain (Khat) was 0.95.
Based on this scenario - WinBUGS did not experience local minima.
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