Two-Tailed p-Values and Coherent Measures of Evidence |
| |
| Authors: | Peter H Peskun |
| |
| Institution: | Mathematics and Statistics, York University, Toronto, Ontario, Canada |
| |
| Abstract: | ABSTRACTIn a test of significance, it is common practice to report the p-value as one way of summarizing the incompatibility between a set of data and a proposed model for the data constructed under a set of assumptions together with a null hypothesis. However, the p-value does have some flaws, one being in general its definition for two-sided tests and a related serious logical one of incoherence, in its interpretation as a statistical measure of evidence for its respective null hypothesis. We shall address these two issues in this article. |
| |
| Keywords: | e-Values Point-null one-sided and interval null hypotheses Stochastically increasing test statistic Unconditional and conditional e-value sampling distributions |
|
|
