Null Hypothesis Significance Testing Defended and Calibrated by Bayesian Model Checking

DOI10.1080/00031305.2019.1699443OpenAlexW2994486096WikidataQ126627198 ScholiaQ126627198MaRDI QIDQ5056972

David R. Bickel

Publication date: 14 December 2022

Published in: The American Statistician (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/00031305.2019.1699443

zbMATH Keywords

hypothesis testingmodel checkingobjective Bayes factorrelative belief ratio\(p\)-value calibrationreproducibility crisis

Mathematics Subject Classification ID

Statistics (62-XX)

Related Items (6)

Publication Policies for Replicable Research and the Community-Wide False Discovery Rate ⋮ Null Hypothesis Significance Testing Interpreted and Calibrated by Estimating Probabilities of Sign Errors: A Bayes-Frequentist Continuum ⋮ Maximum entropy derived and generalized under idempotent probability to address Bayes-frequentist uncertainty and model revision uncertainty: an information-theoretic semantics for possibility theory ⋮ Statistical evidence and surprise unified under possibility theory ⋮ The \(p\)-value interpreted as the posterior probability of explaining the data: applications to multiple testing and to restricted parameter spaces ⋮ Fiducialize statistical significance: transformingp-values into conservative posterior probabilities and Bayes factors

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Error probabilities in default Bayesian hypothesis testing
• Almost sure hypothesis testing and a resolution of the Jeffreys-Lindley paradox
• The one-sided posterior predictive \(p\)-value for Fieller's problem
• Inference after checking multiple Bayesian models for data conflict and applications to mitigating the influence of rejected priors
• Decision making under uncertainty using imprecise probabilities
• Revised standards for statistical evidence
• A general framework for model-based statistics
• A STATISTICAL PARADOX
• A comment on D. V. Lindley's statistical paradox
• Reporting Bayes factors or probabilities to decision makers of unknown loss functions
• Confidence distributions and empirical Bayes posterior distributions unified as distributions of evidential support
• Correcting false discovery rates for their bias toward false positives
• Calibration ofρValues for Testing Precise Null Hypotheses
• A critical evaluation of the current “p‐value controversy”
• Post-Processing Posterior PredictivepValues
• The False Positive Risk: A Proposal Concerning What to Do About p-Values
• The ASA Statement on p-Values: Context, Process, and Purpose

This page was built for publication: Null Hypothesis Significance Testing Defended and Calibrated by Bayesian Model Checking