Admissible ways of merging p-values under arbitrary dependence. / Vovk, Vladimir; Wang, Bin; Wang, Ruodu.

In: The Annals of Statistics, 15.06.2021.

Research output: Contribution to journalArticlepeer-review

Forthcoming

Standard

Admissible ways of merging p-values under arbitrary dependence. / Vovk, Vladimir; Wang, Bin; Wang, Ruodu.

In: The Annals of Statistics, 15.06.2021.

Research output: Contribution to journalArticlepeer-review

Harvard

Vovk, V, Wang, B & Wang, R 2021, 'Admissible ways of merging p-values under arbitrary dependence', The Annals of Statistics.

APA

Vovk, V., Wang, B., & Wang, R. (Accepted/In press). Admissible ways of merging p-values under arbitrary dependence. The Annals of Statistics.

Vancouver

Vovk V, Wang B, Wang R. Admissible ways of merging p-values under arbitrary dependence. The Annals of Statistics. 2021 Jun 15.

Author

Vovk, Vladimir ; Wang, Bin ; Wang, Ruodu. / Admissible ways of merging p-values under arbitrary dependence. In: The Annals of Statistics. 2021.

BibTeX

@article{477cc47c4af04c64adc56673a0dcc0a8,
title = "Admissible ways of merging p-values under arbitrary dependence",
abstract = "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 information 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.",
keywords = "p-values, duality, multiple hypothesis testing, admissibility, e-values",
author = "Vladimir Vovk and Bin Wang and Ruodu Wang",
year = "2021",
month = jun,
day = "15",
language = "English",
journal = "The Annals of Statistics",
issn = "0090-5364",
publisher = "Institute of Mathematical Statistics",

}

RIS

TY - JOUR

T1 - Admissible ways of merging p-values under arbitrary dependence

AU - Vovk, Vladimir

AU - Wang, Bin

AU - Wang, Ruodu

PY - 2021/6/15

Y1 - 2021/6/15

N2 - 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 information 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.

AB - 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 information 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.

KW - p-values

KW - duality

KW - multiple hypothesis testing

KW - admissibility

KW - e-values

M3 - Article

JO - The Annals of Statistics

JF - The Annals of Statistics

SN - 0090-5364

ER -