posthoc step

From: "Pravin Jadhav" pravinj@gmail.com Subject: [NMusers] posthoc step Date: Mon, December 6, 2004 6:35 pm Hello all, This might be a naive question but I am puzzled by the requirement to include POSTHOC command if individual parameters need to be obtained. If I understand correctly, information on individual estimates is available at the convergence in some form (OFV equation includes the summation of difference between individual and population estimate over all subjects). So what is the necessity of posthoc step? Could some explain how does this empirical Bayesian step exactly work? or direct me to some references where this principle is explained. Also, do other equivalent softwares, specifically NLME implemented in S-Plus, work on similar framework (meaning, population parameter estimation followed by Bayesian step)? I apologize for question concerning other software but I thought it might be relevant. Any comments are appreciated. Pravin -- Pravin Jadhav Graduate Student Department of Pharmaceutics MCV/Virginia Commonwealth University DPE1/CDER/OCPB/Food and Drug Administration Phone: (301) 594-5652 Fax: (301) 480-3212