Hostname: page-component-8678677fb7-q5qzn Total loading time: 0 Render date: 2026-10-12T09:18:04.201Z Has data issue: false hasContentIssue false
  • English
  • Français
Accepted manuscript

Exploring the Maximally Sensitive Priors

Published online by Cambridge University Press:  28 July 2026

Nikodem Lewandowski Open the ORCID record for Nikodem Lewandowski [Opens in a new window]  and
Rafał Urbaniak Open the ORCID record for Rafał Urbaniak [Opens in a new window]
Nikodem Lewandowski*
Affiliation:
Institute of Philosophy, University of Gdańsk, Gdańsk, Poland
Rafał Urbaniak
Affiliation:
Basis Research Institute, New York, USA
*
*Corresponding author: Nikodem Lewandowski; nikodem.lewandowski@phdstud.ug.edu.pl
Rights & Permissions [Opens in a new window]

Accessibility of Accepted Manuscripts

Accepted Manuscripts are early, peer-reviewed versions that have not yet been copyedited, typeset, or formally published and may not meet all accessibility standards. A fully formatted accessible version will follow.

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

We explore the Maximum Sensitivity method (MaxSen) of selecting priors for Bayesian inference in the face of severe lack of evidence (Konek, 2013). MaxSen minimizes the need to rely on the epistemic luck of true parameter values falling closely to their prior estimate.We explore the impact of the choice of the scoring method on the recommendations made by MaxSen. It turns out that if we use Kullback-Leibler Divergence (KLD) as a distance measure, the recommendations are the same as that of MaxEnt. We estimate how quickly the recommended prior distribution concentration increases with the planned sample size.

Information

Type
Article
Information
Philosophy of Science , Accepted manuscript , pp. 1 - 21
Copyright
© The Author(s), 2026. Published by Cambridge University Press on behalf of Philosophy of Science Association