Li, W;
Rubio, FJ;
(2022)
On a prior based on the Wasserstein information matrix.
Statistics and Probability Letters
, 190
, Article 109645. 10.1016/j.spl.2022.109645.
Preview |
PDF
WP.pdf - Published Version Download (403kB) | Preview |
Abstract
We introduce a prior for the parameters of univariate continuous distributions, based on the Wasserstein information matrix, which is invariant under reparameterisations. We discuss the links between the proposed prior with information geometry. We present sufficient conditions for the propriety of the posterior distribution for general classes of models. We present a simulation study that shows that the induced posteriors have good frequentist properties.
Type: | Article |
---|---|
Title: | On a prior based on the Wasserstein information matrix |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1016/j.spl.2022.109645 |
Publisher version: | https://doi.org/10.1016/j.spl.2022.109645 |
Language: | English |
Additional information: | © 2022 Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) |
Keywords: | Fisher information matrix, Jeffreys prior, Wasserstein-2 distance, Wasserstein information matrix, Wasserstein prior |
UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
URI: | https://discovery.ucl.ac.uk/id/eprint/10154214 |
Archive Staff Only
![]() |
View Item |