Are neighbour methods preferable to analysis of variance for completely systematic designs? `Silly designs are silly!'

Rosemary Anne Bailey, J.-M. Aza"is, H. Monod

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)

Abstract

It is shown that the usual analysis of a complete-block design is weakly valid under a range of assumptions but that more sophisticated analyses of systematic block designs may not be.
Original languageEnglish
Pages (from-to)655-659
Number of pages5
JournalBiometrika
Volume82
Issue number3
Publication statusPublished - 1995

Keywords

  • complete-block designs
  • efficiency
  • generalised least squares
  • neighbour analysis
  • validity

Fingerprint

Dive into the research topics of 'Are neighbour methods preferable to analysis of variance for completely systematic designs? `Silly designs are silly!''. Together they form a unique fingerprint.

Cite this