RE: posthoc step

From: "Steve Duffull" sduffull@pharmacy.uq.edu.au Subject: RE: [NMusers] posthoc step Date: Wed, December 15, 2004 1:31 am Nick > 1. NONMEM using either the DATA or the PRIOR methods and > WinBugs (Steve, is this correct?) get past the local minimum I think the concept of local minima within the framework of MCMC with variably informative priors a finite sampling space and a finite number of samples is quite a complex issue. But I can say that I tried the problem as discussed, starting from a variety of different initial estimates for the chain and got the same results each time. There may well be initial estimates that I did not try that for the limited number of samples that I ran the chain (5000) may produce different answers. So - I would not want to say that the MCMC process (for the number of iterations that I used) in BUGS avoids the problem - so much as I did not see it. 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