Optimal designs of unbalanced nested designs for determination of measurement precision

Seiichi Yasui, Yoshikazu Ojima

Research output: Contribution to conferencePaperpeer-review

Abstract

Precision of measurement results can be recognized as variance components of random effect models. The variance components are estimated from measurement results that are taken by conducting a collaborative assessment experiment. The measurement results follow a statistical model of a nested design. Although balanced nested designs are widely used, staggered nested designs, which are one of unbalanced nested designs, have the statistical advantage that degrees of freedom in all stages except for the top stage are equal. Thus, the balanced nested designs do not necessarily have the better performance from the statistical viewpoints. In this study, the D-optimal designs are identified in the general nested designs, which including both balanced and unbalanced ones, with considering the practical feasibility of collaborative assessment experiments as well.

Original languageEnglish
Pages211-218
Number of pages8
Publication statusPublished - 1 Jan 2016
Event12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016 - Hamburg, Germany
Duration: 16 Aug 201619 Aug 2016

Conference

Conference12th International Workshop on Intelligent Statistical Quality Control, IWISQC 2016
Country/TerritoryGermany
CityHamburg
Period16/08/1619/08/16

Fingerprint

Dive into the research topics of 'Optimal designs of unbalanced nested designs for determination of measurement precision'. Together they form a unique fingerprint.

Cite this