Test statistics and p-values

Yuri Gurevich, Vladimir Vovk
Proceedings of the Eighth Symposium on Conformal and Probabilistic Prediction and Applications, PMLR 105:89-104, 2019.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v105-gurevich19a, title = {Test statistics and p-values}, author = {Gurevich, Yuri and Vovk, Vladimir}, booktitle = {Proceedings of the Eighth Symposium on Conformal and Probabilistic Prediction and Applications}, pages = {89--104}, year = {2019}, editor = {Gammerman, Alex and Vovk, Vladimir and Luo, Zhiyuan and Smirnov, Evgueni}, volume = {105}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v105/gurevich19a/gurevich19a.pdf}, url = {https://proceedings.mlr.press/v105/gurevich19a.html}, 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.} }
Endnote
%0 Conference Paper %T Test statistics and p-values %A Yuri Gurevich %A Vladimir Vovk %B Proceedings of the Eighth Symposium on Conformal and Probabilistic Prediction and Applications %C Proceedings of Machine Learning Research %D 2019 %E Alex Gammerman %E Vladimir Vovk %E Zhiyuan Luo %E Evgueni Smirnov %F pmlr-v105-gurevich19a %I PMLR %P 89--104 %U https://proceedings.mlr.press/v105/gurevich19a.html %V 105 %X 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.
APA
Gurevich, Y. & Vovk, V.. (2019). Test statistics and p-values. Proceedings of the Eighth Symposium on Conformal and Probabilistic Prediction and Applications, in Proceedings of Machine Learning Research 105:89-104 Available from https://proceedings.mlr.press/v105/gurevich19a.html.

Related Material