The philosophy of Bayes factors and the quantification of statistical evidence

2016/01/13 by Richard D. Morey, Jan-Willem Romeijn, Jan‐Willem Romeijn +1 · 8 citations
Arts and Humanities · Computer Science · #Bayesian Modeling and Causal Inference #Gaussian Processes and Bayesian Inference #Philosophy and History of Science

paper · pdf · doi:10.1016/j.jmp.2015.11.001

openalex publication_date 2016/01/13 · openalex created_date 2016/06/24 · openalex updated_date 2026/08/01

Abstract

A core aspect of science is using data to assess the degree to which data provide evidence for competing claims, hypotheses, or theories. Evidence is by definition something that should change the credibility of a claim in a reasonable person’s mind. However, common statistics, such as significance testing and confidence intervals have no interface with concepts of belief, and thus it is unclear how they relate to statistical evidence. We explore the concept of statistical evidence, and how it can be quantified using the Bayes factor. We also discuss the philosophical issues inherent in the use of the Bayes factor.

Citations

• Fractional Bayes Factors for Model Comparison
• Tumbling toast, Murphy's Law and the fundamental constants
• Subjective probability: A judgment of representativeness
• The gender similarities hypothesis.
• Prior sensitivity in theory testing: An apologia for the Bayes factor
• Default Bayes factors for ANOVA designs
• Residence time and food contact time effects on transfer of Salmonella Typhimurium from tile, wood and carpet: testing the five-second rule
• The Logic of Scientific Discovery
• Bayes Factors

Cited by

• Generalized Jeffreys's approximate objective Bayes factor: Model-selection consistency, finite-sample accuracy, and statistical evidence in 71,126 clinical trial findings
• Inferring Cosmological Parameters with Evidential Physics-Informed Neural Networks
• Black Hole Spectroscopy and Tests of General Relativity with GW250114
• Motor synchrony, social learning and closeness in group play settings
• Testing maximum entropy models with e-values
• A COMPASS to Model Comparison and Simulation-Based Inference in Galactic Chemical Evolution
• Domain general frontoparietal regions show modality-dependent coding of auditory and visual rules
• How to become a Bayesian in eight easy steps: An annotated reading list