Valid randomisation for the first-difference analysis

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

Valid randomisation for the first-difference analysis

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

Research output: Contribution to journal › Article › peer-review

Abstract

A general method is presented for randomising a block design while preserving the neighbour relationships between treatments. The randomisation possesses validity properties for the first-difference analysis introduced by Besag and Kempton (1986). The estimators of treatment differences are unbiased, and the paper shows how to calculate quadratic estimators of their variance, which are unbiased if treatment effects and plot effects are additive. Simplifications, which appear when the design is neighbour-balanced, are described and illustrated.

Original language	English
Pages (from-to)	91-106
Number of pages	16
Journal	Australian Journal of Statistics
Volume	38
Issue number	1
Publication status	Published - 1996

Keywords

neighbour analysis
neighbour design
quadratic unbiased estimator
valid randomisation

Cite this

@article{76ba37780a1b4ad6b1a5f25e05761152,

title = "Valid randomisation for the first-difference analysis",

abstract = "A general method is presented for randomising a block design while preserving the neighbour relationships between treatments. The randomisation possesses validity properties for the first-difference analysis introduced by Besag and Kempton (1986). The estimators of treatment differences are unbiased, and the paper shows how to calculate quadratic estimators of their variance, which are unbiased if treatment effects and plot effects are additive. Simplifications, which appear when the design is neighbour-balanced, are described and illustrated.",

keywords = "neighbour analysis, neighbour design, quadratic unbiased estimator, valid randomisation",

author = "H. Monod and J.-M. Aza{"}is and Bailey, {Rosemary Anne}",

year = "1996",

language = "English",

volume = "38",

pages = "91--106",

journal = "Australian Journal of Statistics",

number = "1",

}

TY - JOUR

T1 - Valid randomisation for the first-difference analysis

AU - Monod, H.

AU - Aza"is, J.-M.

AU - Bailey, Rosemary Anne

PY - 1996

Y1 - 1996

N2 - A general method is presented for randomising a block design while preserving the neighbour relationships between treatments. The randomisation possesses validity properties for the first-difference analysis introduced by Besag and Kempton (1986). The estimators of treatment differences are unbiased, and the paper shows how to calculate quadratic estimators of their variance, which are unbiased if treatment effects and plot effects are additive. Simplifications, which appear when the design is neighbour-balanced, are described and illustrated.

AB - A general method is presented for randomising a block design while preserving the neighbour relationships between treatments. The randomisation possesses validity properties for the first-difference analysis introduced by Besag and Kempton (1986). The estimators of treatment differences are unbiased, and the paper shows how to calculate quadratic estimators of their variance, which are unbiased if treatment effects and plot effects are additive. Simplifications, which appear when the design is neighbour-balanced, are described and illustrated.

KW - neighbour analysis

KW - neighbour design

KW - quadratic unbiased estimator

KW - valid randomisation

M3 - Article

VL - 38

SP - 91

EP - 106

JO - Australian Journal of Statistics

JF - Australian Journal of Statistics

IS - 1

ER -

Valid randomisation for the first-difference analysis

Abstract

Keywords

Fingerprint

Cite this