What is it about?
A popular response to the replication crisis is to transform p-values into Bayes factors or posterior probabilities. This paper proposes a way to do that by using Occam's razor to simplify prior distributions.
Featured Image
Why is it important?
The replication crisis is caused in part by false positives resulting from null hypothesis significance testing at the 0.05 level of significance. This paper uses Occam's razor to argue for reducing the significance level to 0.001.
Perspectives
For further reading, follow the "Related papers" link.
David R. Bickel
University of North Carolina at Greensboro
Read the Original
This page is a summary of: Sharpen statistical significance: Evidence thresholds and Bayes factors sharpened into Occam's razor, Stat, January 2019, Wiley,
DOI: 10.1002/sta4.215.
You can read the full text:
Resources
Contributors
The following have contributed to this page
