Online Program Home
  My Program

Abstract Details

Activity Number: 452 - Methodological and Computational Advances in Bayesian Design for Scientific and Industrial Experimentation
Type: Topic Contributed
Date/Time: Wednesday, August 2, 2017 : 8:30 AM to 10:20 AM
Sponsor: Section on Bayesian Statistical Science
Abstract #323101
Title: Bayesian A-Optimal Design of Experiment with Quantitative and Qualitative Responses
Author(s): Lulu Kang*
Companies: Illinois Institute of Technology-Department of Applied Mathematics
Keywords: A-optimal design ; Block coordinate descent ; Conditional model ; logistic model ; Particle swarm optimization ; qualitative response
Abstract:

In this paper, we propose a new experimental design method for the experiments that contain both quantitative and qualitative outputs. We first develop the A-optimal design criterion, based on the joint quantitative-qualitative model that has been introduced in the literature. The traditional exchange-point algorithm can no longer be applied to the A-optimal criterion due to the complex model structure of the joint quantitative-qualitative model. Thus we develop a new block coordinate descent algorithm and combine it with particle swarm optimization. Simulation examples are used to show the efficiency and effectiveness of the proposed optimal design criterion and construction method.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association