Inferential Statistics as Descriptive Statistics: There Is No Replication Crisis if We Don’t Expect Replication

DOI10.1080/00031305.2018.1543137OpenAlexW2919176916MaRDI QIDQ5868261

Sander Greenland, David Trafimow, Valentin Amrhein

Publication date: 20 September 2022

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

Full work available at URL: https://doi.org/10.1080/00031305.2018.1543137

zbMATH Keywords

hypothesis teststatistical modelconfidence intervalreplicationposterior probabilitysignificance test\(P\)-valueselective reportingauxiliary hypothesesunreplicable research

Mathematics Subject Classification ID

Statistics (62-XX)

Related Items (7)

Publication Policies for Replicable Research and the Community-Wide False Discovery Rate ⋮ Toward Replicability With Confidence Intervals for the Exceedance Probability ⋮ P-values don’t measure evidence ⋮ Connecting simple and precise P‐values to complex and ambiguous realities (includes rejoinder to comments on “Divergence vs. decision P‐values”) ⋮ A Statistical Basis for Reporting Strength of Evidence as Pool Reduction ⋮ Moving to a World Beyond “p < 0.05” ⋮ On Causal Inferences for Personalized Medicine: How Hidden Causal Assumptions Led to Erroneous Causal Claims About the D-Value

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Computer Age Statistical Inference
• Testing Statistical Hypotheses of Equivalence and Noninferiority
• Sampling and Bayes' Inference in Scientific Modelling and Robustness
• P Values for Composite Null Models
• Asymptotic Distribution of P Values in Composite Null Models
• Abandon Statistical Significance

This page was built for publication: Inferential Statistics as Descriptive Statistics: There Is No Replication Crisis if We Don’t Expect Replication