Re: posthoc step

From: "Pravin Jadhav" pravinj@gmail.com Subject: Re: [NMusers] posthoc step Date: Tue, December 7, 2004 2:38 pm Thank you all for replying to my query. I appreciate it. I was not clear on these aspect. I was trying to recalculate the OFV value using the NONMEM output, I got confused and was not sure about the process. Diane, I tried your suggestion. .....until one runs POSTHOC the IPRED is the same as PRED for FO because eta isn't evaluated. (try it and see)...I guess it is much more clear now. However, I am still interested in specifics of the POSTHOC step. As explained many times, it uses population estimates as priors to calculate individual estimates. My question is- how? and where do I get the details of so called empirical Bayesian step?. Is it using MCMC algorithm like what WINBUGS uses? Thanks. Pravin