Re: posthoc step

From: "Nick Holford" n.holford@auckland.ac.nz Subject: Re: [NMusers] posthoc step Date: Tue, December 7, 2004 3:02 pm Pravin, As I understand the mysteries of NONMEM, it computes Maximum A Posteriori Bayesian (MAPB) estimates from a prior parameter distribution using the population estimates of THETA (the mean) and OMEGA (the uncertainty). This is done after each iteration with FOCE and with the final estimates with FO and the POSTHOC option. MAPB estimates can be obtained with an objective function like this: SS = sum i=1 to Nobs [(Yhati - Yobsi)**2/SIGMA**2] + sum k=1 to NPAR [(THETAhatk - THETAki)/OMEGAhatk**2)] where Yhat is the prediction of the observation, Yobs, using individual estimates, THETAki. THETAhatk is the population estimate of the kth THETA parameter. OMEGAhatk is the estimate of OMEGA for the kth THETA parameter. I am sure this is a oversimplification of what NONMEM actually does but this should give you an idea. Sheiner LB, Beal SL. Bayesian individualization of pharmacokinetics: simple implementation and comparison with non-Bayesian methods. J Pharm Sci 1982;71(12):1344-8 Nick -- Nick Holford, Dept Pharmacology & Clinical Pharmacology University of Auckland, 85 Park Rd, Private Bag 92019, Auckland, New Zealand email:n.holford@auckland.ac.nz tel:+64(9)373-7599x86730 fax:373-7556 http://www.health.auckland.ac.nz/pharmacology/staff/nholford/