Department of Statistics Seminar
North Carolina State University

presents

Gary L. Rosner

Duke University Medical Center and Institute of Statistics and Decision Sciences, Duke University

"Bayesian Population Pharmacokinetic and Pharmacodynamic Analyses Using Mixture Models"

ABSTRACT

Population studies of the pharmacokinetics or pharmacodynamics of drugs help us learn about the variability in drug disposition and effects, information that can be used to treat future patients at safe and effective doses. Inference in such analyses is complex, often involving nonlinear functions to model the observations as functions of time and/or other covariates. We present a new approach to population modeling based on a weighted mixture of normal distributions having random weights and means. This method allows estimation of underlying continous population distributions without prespecifying the parametric form or shape of these probability distributions. Additionally, nonparametric regression of pharmacokinetic or dynamic parameters on patient covariates can be carried out while estimating the underlying distributions. Two examples illustrate the method and its flexibility. (I collaborated with Peter Mueller of the Institute of Statistics and Decision Sciences, Duke University, on this research.)

Friday, January 8, 1999

3:35 - 4:35 pm

206 Cox Hall

Refreshments will be served on the second floor of Dabney Hall (left of Room 222) at 3:00 pm.