Test statistics and p-values

Yuri Gurevich; Vladimir Vovk

Test statistics and p-values

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

We point out that the traditional notion of test statistic is too narrow, even for the purpose of conformal prediction. The most natural generalization of the traditional notion happens to be too wide. We propose another natural generalization which is arguably the widest reasonable generalization. The study is restricted to simple statistical hypotheses.

Original language	English
Title of host publication	Proceedings of Machine Learning Research
Editors	Alex Gammerman, Vladimir Vovk, Zhiyuan Luo, Evgueni Smirnov
Pages	89-104
Number of pages	16
Volume	105
Publication status	Published - 29 Aug 2019

Keywords

exact p-value
randomized p-value
test statistic
lexicographic order

Access to Document

http://proceedings.mlr.press/v105/gurevich19a/gurevich19a.pdf

Cite this

@inbook{2964d5e35793485fb5a4f8cf3c68a9a6,

title = "Test statistics and p-values",

abstract = "We point out that the traditional notion of test statistic is too narrow, even for the purpose of conformal prediction. The most natural generalization of the traditional notion happens to be too wide. We propose another natural generalization which is arguably the widest reasonable generalization. The study is restricted to simple statistical hypotheses.",

keywords = "exact p-value, randomized p-value, test statistic, lexicographic order",

author = "Yuri Gurevich and Vladimir Vovk",

year = "2019",

month = aug,

day = "29",

language = "English",

volume = "105",

pages = "89--104",

editor = "Alex Gammerman and Vladimir Vovk and Zhiyuan Luo and Evgueni Smirnov",

booktitle = "Proceedings of Machine Learning Research",

}

TY - CHAP

T1 - Test statistics and p-values

AU - Gurevich, Yuri

AU - Vovk, Vladimir

PY - 2019/8/29

Y1 - 2019/8/29

N2 - We point out that the traditional notion of test statistic is too narrow, even for the purpose of conformal prediction. The most natural generalization of the traditional notion happens to be too wide. We propose another natural generalization which is arguably the widest reasonable generalization. The study is restricted to simple statistical hypotheses.

AB - We point out that the traditional notion of test statistic is too narrow, even for the purpose of conformal prediction. The most natural generalization of the traditional notion happens to be too wide. We propose another natural generalization which is arguably the widest reasonable generalization. The study is restricted to simple statistical hypotheses.

KW - exact p-value

KW - randomized p-value

KW - test statistic

KW - lexicographic order

M3 - Chapter

VL - 105

SP - 89

EP - 104

BT - Proceedings of Machine Learning Research

A2 - Gammerman, Alex

A2 - Vovk, Vladimir

A2 - Luo, Zhiyuan

A2 - Smirnov, Evgueni

ER -