Exclusive Content & Downloads from ASQ

Incorporating Prior Information in Optimal Design for Model Selection

Summary:  [This abstract is based on the authors’ abstract.] Experimental designs are used in screening to identify significant effects from a large set of candidate effects. This study introduces a design criterion that seeks to maximize the ability to discriminate between models. The Bayesian criterion is based on the Hellinger distance between predictive distributions under competing models. Techniques for evaluating the criterion and searching for optimal designs are presented. The criterion is illustrated with examples that consider regular and nonregular designs, robust designs, and situations with partial prior knowledge of which effects are significant.

Anyone with a subscription, including Site and Enterprise members, can access this article.

Other Ways to Access content:

Join ASQ

Join ASQ as a Full member. Enjoy all the ASQ member benefits including access to many online articles.

  • Topics: Design of Experiments, Statistics
  • Keywords: Bayesian methods, Design of experiments (DOE), Effects, Hierarchical Experiments, Alias, Model discrimination, Effect sparsity.
  • Author: Bingham, Derek R.; Chipman, Hugh A.
  • Journal: Technometrics