The Bayes' factor: the coherent measure for hypothesis conrmation

Franco Taroni; Silvia Bozza; Paolo Garbolino; Colin Aitken

The Bayes' factor: the coherent measure for hypothesis conrmation

Franco Taroni, Silvia Bozza, Paolo Garbolino, Colin Aitken

School of Mathematics

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

Abstract / Description of output

What have been called `Bayesian confirmation measures' or `evidential support measures' offer a numerical expression for the impact of a piece of evidence on a judicial hypothesis of interest. The Bayes' factor, sometimes 8 simply called the `likelihood ratio', represents the best measure of the value of the evidence. It satisfies a number of necessary conditions on normative logical adequacy. It is shown that the same cannot be said for alternative 10 expressions put forward by some legal and forensic quarters. A list of desiderata are given that support the choice of the Bayes' factor as the best measure for quantification of the value of evidence.

Original language	English
Number of pages	20
Journal	Law, Probability & Risk
Publication status	Accepted/In press - 10 Nov 2021

Access to Document

BF_coherent measure-04112021Accepted author manuscript, 343 KB

Cite this

@article{838b0d96bb4f415a97970abc73d91596,

title = "The Bayes' factor: the coherent measure for hypothesis conrmation",

abstract = "What have been called `Bayesian confirmation measures' or `evidential support measures' offer a numerical expression for the impact of a piece of evidence on a judicial hypothesis of interest. The Bayes' factor, sometimes 8 simply called the `likelihood ratio', represents the best measure of the value of the evidence. It satisfies a number of necessary conditions on normative logical adequacy. It is shown that the same cannot be said for alternative 10 expressions put forward by some legal and forensic quarters. A list of desiderata are given that support the choice of the Bayes' factor as the best measure for quantification of the value of evidence.",

author = "Franco Taroni and Silvia Bozza and Paolo Garbolino and Colin Aitken",

year = "2021",

month = nov,

day = "10",

language = "English",

journal = "Law, Probability & Risk",

issn = "1470-8396",

publisher = "Oxford University Press",

}

TY - JOUR

T1 - The Bayes' factor: the coherent measure for hypothesis conrmation

AU - Taroni, Franco

AU - Bozza, Silvia

AU - Garbolino, Paolo

AU - Aitken, Colin

PY - 2021/11/10

Y1 - 2021/11/10

N2 - What have been called `Bayesian confirmation measures' or `evidential support measures' offer a numerical expression for the impact of a piece of evidence on a judicial hypothesis of interest. The Bayes' factor, sometimes 8 simply called the `likelihood ratio', represents the best measure of the value of the evidence. It satisfies a number of necessary conditions on normative logical adequacy. It is shown that the same cannot be said for alternative 10 expressions put forward by some legal and forensic quarters. A list of desiderata are given that support the choice of the Bayes' factor as the best measure for quantification of the value of evidence.

AB - What have been called `Bayesian confirmation measures' or `evidential support measures' offer a numerical expression for the impact of a piece of evidence on a judicial hypothesis of interest. The Bayes' factor, sometimes 8 simply called the `likelihood ratio', represents the best measure of the value of the evidence. It satisfies a number of necessary conditions on normative logical adequacy. It is shown that the same cannot be said for alternative 10 expressions put forward by some legal and forensic quarters. A list of desiderata are given that support the choice of the Bayes' factor as the best measure for quantification of the value of evidence.

M3 - Article

SN - 1470-8396

JO - Law, Probability & Risk

JF - Law, Probability & Risk

ER -

The Bayes' factor: the coherent measure for hypothesis conrmation

Abstract / Description of output

Access to Document

Fingerprint

Cite this