What is it about?
Is there enough evidence to draw a conclusion? Does the evidence make the conclusion more probable than it was? The way the strength of evidence is quantified depends on which question is asked. This paper argues that the likeliness of a composite hypothesis is the only number that addresses both questions. The likeliness is closely related to the likelihood ratio statistic and complies with the general law of likelihood.
Photo by Kelsey Mirehouse on Unsplash
Why is it important?
The likeliness of a composite hypothesis is a simple way to quantify its strength of evidence without the use of a prior distribution.
Read the Original
This page is a summary of: The sufficiency of the evidence, the relevancy of the evidence, and quantifying both with a single number, Statistical Methods & Applications, January 2021, Springer Science + Business Media, DOI: 10.1007/s10260-020-00553-3.
You can read the full text:
The following have contributed to this page