A Cantelli-type inequality for constructing non-parametric p-boxes based on exchangeability

Troffaes, Matthias C.M.; Basu, Tathagata

A Cantelli-type inequality for constructing non-parametric p-boxes based on exchangeability

Troffaes, Matthias C.M.; Basu, Tathagata

Authors

Professor Matthias Troffaes matthias.troffaes@durham.ac.uk
Professor

Tathagata Basu

Contributors

Jasper De Bock
Editor

Cassio P. de Campos
Editor

Gert de Cooman
Editor

Erik Quaeghebeur
Editor

Gregory Wheeler
Editor

Abstract

In this paper we prove a new probability inequality that can be used to construct p-boxes in a non-parametric fashion, using the sample mean and sample standard deviation instead of the true mean and true standard deviation. The inequality relies only on exchangeability and boundedness.

Citation

Troffaes, M. C., & Basu, T. (2019). A Cantelli-type inequality for constructing non-parametric p-boxes based on exchangeability. In J. D. Bock, C. P. . D. Campos, G. D. Cooman, E. Quaeghebeur, & G. Wheeler (Eds.), Proceedings of the Eleventh International Symposium on Imprecise Probabilities : Theories and Applications (386-393)

Conference Name	ISIPTA'19
Conference Location	Ghent
Acceptance Date	Apr 26, 2019
Publication Date	2019
Deposit Date	Jun 17, 2019
Publicly Available Date	Jun 18, 2019
Pages	386-393
Series Title	Proceedings of machine learning research
Series Number	103
Series ISSN	2640-3498
Book Title	Proceedings of the Eleventh International Symposium on Imprecise Probabilities : Theories and Applications.
Public URL	https://durham-repository.worktribe.com/output/1142573
Publisher URL	http://proceedings.mlr.press/v103/troffaes19a.html

Files

Accepted Conference Proceeding (191 Kb)
PDF

Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/

Copyright Statement
This paper has been published under a Creative Commons Attribution 4.0 International License specified at http://creativecommons.org/licenses/by/4.0/legalcode (human readable summary at http://creativecommons.org/licenses/by/4.0).