Bayesian D-optimal design issues for binomial generalized linear model screening designs

Edgar Hassler, Douglas Montgomery, Rachel T. Silvestrini

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Bayesian D-optimal designs have become computationally feasible to construct for simple prior distributions. Some parameter values give rise to models that have little utility to the practitioner for effect screening. For some generalized linear models such as the binomial, inclusion of such models can cause the optimal design to spread out toward the boundary of the design space. This can reduce the D-efficiency of the design over much of the parameter space and result in the Bayesian D-optimal criterion's divergence from the concerns of a practitioner designing a screening experiment.

Original languageEnglish (US)
Title of host publicationFrontiers in Statistical Quality Control 10
PublisherKluwer Academic Publishers
Pages337-353
Number of pages17
Volume11
ISBN (Print)9783319123547
DOIs
StatePublished - 2015
Event11th International Workshop on Intelligent Statistical Quality Control, 2013 - Sydney, Australia
Duration: Aug 20 2013Aug 23 2013

Other

Other11th International Workshop on Intelligent Statistical Quality Control, 2013
CountryAustralia
CitySydney
Period8/20/138/23/13

Keywords

  • Challenger data set
  • Confidence intervals
  • Non-linear designs

ASJC Scopus subject areas

  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Bayesian D-optimal design issues for binomial generalized linear model screening designs'. Together they form a unique fingerprint.

Cite this