A new angle on the t-test

Graham R. Wood; David J. Saville

doi:10.1111/1467-9884.00301

A new angle on the t-test

Graham R. Wood, David J. Saville^*

^*Corresponding author for this work

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

3 Citations (Scopus)

Abstract

R. A. Fisher's early work on linear models relied heavily on his knowledge of n-dimensional geometry. To illustrate this, we present an elementary, complete, modern day account of Fisher's geometric approach for the simple case of a paired samples t-test for a sample size of 3. A natural consequence of this approach is a surprisingly simple and explicit expression for the p-value.

Original language	English
Pages (from-to)	99-104
Number of pages	6
Journal	Journal of the Royal Statistical Society Series D: The Statistician
Volume	51
Issue number	1
DOIs	https://doi.org/10.1111/1467-9884.00301
Publication status	Published - 2002

Keywords

Linear algebra
p-value
Paired samples t-test
Vector geometry

Access to Document

10.1111/1467-9884.00301

Link to publication in Scopus

Cite this

@article{ec3dbb8bcffc487da3be41d149aad9c4,

title = "A new angle on the t-test",

abstract = "R. A. Fisher's early work on linear models relied heavily on his knowledge of n-dimensional geometry. To illustrate this, we present an elementary, complete, modern day account of Fisher's geometric approach for the simple case of a paired samples t-test for a sample size of 3. A natural consequence of this approach is a surprisingly simple and explicit expression for the p-value.",

keywords = "Linear algebra, p-value, Paired samples t-test, Vector geometry",

author = "Wood, {Graham R.} and Saville, {David J.}",

year = "2002",

doi = "10.1111/1467-9884.00301",

language = "English",

volume = "51",

pages = "99--104",

journal = "Journal of the Royal Statistical Society Series D: The Statistician",

issn = "0039-0526",

number = "1",

}

TY - JOUR

T1 - A new angle on the t-test

AU - Wood, Graham R.

AU - Saville, David J.

PY - 2002

Y1 - 2002

N2 - R. A. Fisher's early work on linear models relied heavily on his knowledge of n-dimensional geometry. To illustrate this, we present an elementary, complete, modern day account of Fisher's geometric approach for the simple case of a paired samples t-test for a sample size of 3. A natural consequence of this approach is a surprisingly simple and explicit expression for the p-value.

AB - R. A. Fisher's early work on linear models relied heavily on his knowledge of n-dimensional geometry. To illustrate this, we present an elementary, complete, modern day account of Fisher's geometric approach for the simple case of a paired samples t-test for a sample size of 3. A natural consequence of this approach is a surprisingly simple and explicit expression for the p-value.

KW - Linear algebra

KW - p-value

KW - Paired samples t-test

KW - Vector geometry

UR - http://www.scopus.com/inward/record.url?scp=0040076615&partnerID=8YFLogxK

U2 - 10.1111/1467-9884.00301

DO - 10.1111/1467-9884.00301

M3 - Article

AN - SCOPUS:0040076615

VL - 51

SP - 99

EP - 104

JO - Journal of the Royal Statistical Society Series D: The Statistician

JF - Journal of the Royal Statistical Society Series D: The Statistician

SN - 0039-0526

IS - 1

ER -

A new angle on the t-test

Abstract

Keywords

Access to Document

Fingerprint

Cite this