Fractional factorial split-plot designs with minimum aberration and maximum estimation capacity

Rahul Mukerjee*, Kai Tai Fang

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

30 Citations (Scopus)

Abstract

Considering general prime or prime powered factorials, we give a finite projective geometric formulation for regular fractional factorial split-plot designs. This provides a unified framework for such designs and facilitates their systematic study under the criteria of minimum aberration and minimum secondary aberration; the latter criterion is considered to achieve finer discrimination. We investigate the role of complementary subsets in this context and observe that, unlike in classical fractional factorials, two such complementary subsets have to be handled simultaneously. Criteria based on estimation capacity are also studied to provide further statistical justification for our results. Finally, applications of the results to specific cases are summarized as tables.

Original languageEnglish
Pages (from-to)885-903
Number of pages19
JournalStatistica Sinica
Volume12
Issue number3
Publication statusPublished - Jul 2002
Externally publishedYes

Scopus Subject Areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

User-Defined Keywords

  • Complementary subsets
  • Finite projective geometry
  • Minimum secondary aberration
  • Sub plot
  • Two-phase randomization
  • Whole plot
  • Word-length pattern

Fingerprint

Dive into the research topics of 'Fractional factorial split-plot designs with minimum aberration and maximum estimation capacity'. Together they form a unique fingerprint.

Cite this