Skip to main content

Using Bayes Factors to evaluate evidence for no effect: examples from the SIPS project

Coulton, Simon, Heather, Nick, Dienes, Zoltan (2017) Using Bayes Factors to evaluate evidence for no effect: examples from the SIPS project. Addiction, . ISSN 0965-2140. (doi:10.1111/add.14002)

MS Word - Author's Accepted Manuscript
Download (44kB)
[img]
Official URL
http://10.1111/add.14002

Abstract

ABSTRACT

Method: We consider a case where inappropriate conclusions were publicly drawn based on significance testing, namely the SIPS Project (Screening and Intervention Programme for Sensible drinking), a pragmatic, cluster-randomized controlled trial in each of two healthcare settings and in the criminal justice system. We show how Bayes Factors can disambiguate the non-significant findings from the SIPS Project and thus determine whether the findings represent evidence of absence or absence of evidence. We show how to model the sort of effects that could be expected, and how to check the robustness of the Bayes Factors.

Conclusion: Scientists who find non-significant results should suspend judgment – unless they calculate a Bayes Factor to indicate either that there is evidence for H0 over a (well-justified) H1, or else that more data is needed.

Item Type: Article
DOI/Identification number: 10.1111/add.14002
Uncontrolled keywords: Non-significance, Bayes Factors, Evidence of absence, Alcohol brief interventions, SIPS Project
Subjects: H Social Sciences
H Social Sciences > HM Sociology
Divisions: Faculties > Social Sciences > School of Social Policy Sociology and Social Research > Centre for Health Services Studies
Depositing User: Paula Loader
Date Deposited: 24 Aug 2017 15:01 UTC
Last Modified: 22 Jan 2020 04:10 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/62941 (The current URI for this page, for reference purposes)
Coulton, Simon: https://orcid.org/0000-0002-7704-3274
  • Depositors only (login required):

Downloads

Downloads per month over past year