PLACE: 1201 Coover

SPEAKER:
Ken Ryan
Department of Statistics
Iowa State University

TITLE:
Estimating Expected Information Gains for Experimental Designs With Application to the Random Fatigue-Limit Model
 

ABSTRACT:
Expected gain in Shannon information is commonly suggested as a Bayesian design evaluation criterion.  However, examples in which expected information gains have been successfully used in identifying Bayes optimal designs are both few and typically quite simplistic.  This paper discusses in general some properties of estimators of expected information gains based on Markov chain Monte Carlo (MCMC) and Laplacian approximations.  We then investigate some issues that arise when applying these methods to the problem of experimental design in the (technically non-trivial) random fatigue-limit model of Pascual and Meeker (1999).  An example comparing follow-up designs for a laminate panel study is provided.

COFFEE: 12:45 p.m., 104 Snedecor Hall