Friday, February 9, 2001, from 9:00am to 10:20am in room C-301, Padelford Hall, University of Washington Campus.
Speaker: James Burke, University of Washington
Title: Non-Parametric Population Analysis
Population analysis is the methodology used to study inter-subject variability in studies designed to analyze a phenomenon associated with a targeted population. For example, the methodology is widely used in pharmacokinetic studies since it is the key to understanding how drugs behave in humans and animals. In non-parametric population one uses a maximum likelihood objective function to directly approximate the distribution of the underlying parameters over the set of Borel probability measures. It is well known that this infinite dimensional constrained optimization problem has an equivalent representation as a finite dimensional convex program. We first review this equivalence and then show how interior point methodology can be applied to efficiently obtain approximate solutions.