Admissible ways of merging p-values under arbitrary dependence
By Vladimir G Vovk, Bin Wang, Ruodu Wang. Annals of Statistics, 2020
82 citations recorded by the source corpus.
Methods of merging several p-values into a single p-value are important in their own right and widely used in multiple hypothesis testing. This paper is the first to systematically study the admissibility (in Wald's sense) of p-merging functions and their domination structure, without any assumptions on the dependence structure of the input p-values. As a technical tool we use the notion of e-values, which are alternatives to p-values recently promoted by several authors. We obtain several results on the representation of admissible p-merging functions via e-values and on (in)admissibility of existing p-merging functions. By introducing new admissible p-merging functions, we show that some classic merging methods can be strictly improved to enhance power without compromising validity under arbitrary dependence.
Subfields: Management Science and Operations Research, Statistics and Probability
View Paper: https://www.semanticscholar.org/paper/2e7374553f066078b5d29256e1b9db8982214a20
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Management Science and Operations Research
In Statistics and Probability
Citations in the corpus
- False discovery rate control with e‐values (2020, methodology): “On a related note, calibration to e-values serves as a crucial intermediate step in combining p-values under arbitrary dependence for testing a global null (Vovk et al., 2020, section 5).”
- E-values: Calibration, combination and applications (2019, unknown): “It is interesting that any p-to-e merging function is dominated by a p-to-e merging function of this form [Vovk et al., 2020, Theorem 4.1].”