
Safe Testing
We present a new theory of hypothesis testing. The main concept is the S...
read it

True and false discoveries with evalues
We discuss controlling the number of false discoveries using evalues in...
read it

True and false discoveries with independent evalues
In this note we use evalues (a nonBayesian version of Bayes factors) i...
read it

Technical Issues in the Interpretation of Svalues and Their Relation to Other Information Measures
An extended technical discussion of Svalues and unconditional informati...
read it

On Conflicting and Conflicting Values
Values are things that are important to us. Actions activate values  th...
read it

On Conforming and Conflicting Values
Values are things that are important to us. Actions activate values  th...
read it

Probabilistic Tools for the Analysis of Randomized Optimization Heuristics
This chapter collects several probabilistic tools that proved to be usef...
read it
Testing with p*values: Between pvalues and evalues
We introduce the notion of p*values (p*variables), which generalizes pvalues (pvariables) in several senses. The new notion has four natural interpretations: probabilistic, operational, Bayesian, and frequentist. The simplest interpretation of a p*value is the average of several pvalues. We show that there are four equivalent definitions of p*values. The randomized p*test is proposed, which is a randomized version of the simple ptest. Admissible calibrators of p*values to and from pvalues and evalues are obtained with nice mathematical forms, revealing the role of p*values as a bridge between pvalues and evalues. The notion of p*values becomes useful in many situations even if one is only interested in pvalues and evalues. In particular, tests based on p*values can be applied to improve several classic methods for pvalues and evalues.
READ FULL TEXT
Comments
There are no comments yet.