Significance testing, p-values and the principle of total evidence

Bengt Autzen

doi:10.1007/s13194-016-0138-0

Significance testing, p-values and the principle of total evidence

Bengt Autzen

University of Bristol

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

Abstract

The paper examines the claim that significance testing violates the Principle of Total Evidence (PTE). I argue that p-values violate PTE for two-sided tests but satisfy PTE for one-sided tests invoking a sufficient test statistic independent of the preferred theory of evidence. While the focus of the paper is to evaluate a particular claim about the relationship of significance testing and PTE, I clarify the reading of this methodological principle along the way.

Original language	English
Pages (from-to)	281-295
Number of pages	15
Journal	European Journal for Philosophy of Science
Volume	6
Issue number	2
DOIs	https://doi.org/10.1007/s13194-016-0138-0
Publication status	Published - 1 May 2016
Externally published	Yes

Keywords

Bayes
Error statistics
Evidence
Law of likelihood
p-values
Principle of total evidence
Significance testing

Access to Document

10.1007/s13194-016-0138-0

Cite this

@article{69e50aa25c2e4aaca9ebb1e1405a42ae,

title = "Significance testing, p-values and the principle of total evidence",

abstract = "The paper examines the claim that significance testing violates the Principle of Total Evidence (PTE). I argue that p-values violate PTE for two-sided tests but satisfy PTE for one-sided tests invoking a sufficient test statistic independent of the preferred theory of evidence. While the focus of the paper is to evaluate a particular claim about the relationship of significance testing and PTE, I clarify the reading of this methodological principle along the way.",

keywords = "Bayes, Error statistics, Evidence, Law of likelihood, p-values, Principle of total evidence, Significance testing",

author = "Bengt Autzen",

note = "Publisher Copyright: {\textcopyright} 2016, The Author(s).",

year = "2016",

month = may,

day = "1",

doi = "10.1007/s13194-016-0138-0",

language = "English",

volume = "6",

pages = "281--295",

journal = "European Journal for Philosophy of Science",

issn = "1879-4912",

publisher = "Springer Netherlands",

number = "2",

}

TY - JOUR

T1 - Significance testing, p-values and the principle of total evidence

AU - Autzen, Bengt

PY - 2016/5/1

Y1 - 2016/5/1

N2 - The paper examines the claim that significance testing violates the Principle of Total Evidence (PTE). I argue that p-values violate PTE for two-sided tests but satisfy PTE for one-sided tests invoking a sufficient test statistic independent of the preferred theory of evidence. While the focus of the paper is to evaluate a particular claim about the relationship of significance testing and PTE, I clarify the reading of this methodological principle along the way.

AB - The paper examines the claim that significance testing violates the Principle of Total Evidence (PTE). I argue that p-values violate PTE for two-sided tests but satisfy PTE for one-sided tests invoking a sufficient test statistic independent of the preferred theory of evidence. While the focus of the paper is to evaluate a particular claim about the relationship of significance testing and PTE, I clarify the reading of this methodological principle along the way.

KW - Bayes

KW - Error statistics

KW - Evidence

KW - Law of likelihood

KW - p-values

KW - Principle of total evidence

KW - Significance testing

UR - https://www.scopus.com/pages/publications/84963771415

U2 - 10.1007/s13194-016-0138-0

DO - 10.1007/s13194-016-0138-0

M3 - Article

AN - SCOPUS:84963771415

SN - 1879-4912

VL - 6

SP - 281

EP - 295

JO - European Journal for Philosophy of Science

JF - European Journal for Philosophy of Science

IS - 2

ER -

Significance testing, p-values and the principle of total evidence

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this