Babic, Boris (2018) A Theory of Epistemic Risk. [Preprint]

Preview

Text babic_ter.pdf Download (816kB) | Preview

Abstract

I propose a general alethic theory of epistemic risk according to which the riskiness of an agent's credence function encodes their relative sensitivity to different types of graded error. After motivating and mathematically developing this approach, I show that the epistemic risk function is a scaled reflection of expected inaccuracy (a quantity also known as generalized information entropy). This duality between risk and information enables us to explore the relationship between attitudes to epistemic risk, the choice of scoring rule in epistemic utility theory, and the selection of priors in Bayesian epistemology more generally (including the Laplacean principle of indifference)

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Babic, Boris babic917@gmail.com
Keywords:	risk, accuracy, information, scoring rules
Subjects:	Specific Sciences > Mathematics > Epistemology General Issues > Decision Theory Specific Sciences > Economics Specific Sciences > Probability/Statistics
Depositing User:	Boris Babic
Date Deposited:	22 Aug 2018 15:14
Last Modified:	22 Aug 2018 15:14
Item ID:	14961
Subjects:	Specific Sciences > Mathematics > Epistemology General Issues > Decision Theory Specific Sciences > Economics Specific Sciences > Probability/Statistics
Date:	2018
URI:	https://philsci-archive.pitt.edu/id/eprint/14961

Available Versions of this Item

• A Theory of Epistemic Risk. (deposited 22 Aug 2018 15:14) [Currently Displayed]
  • A Theory of Epistemic Risk. (deposited 03 Oct 2018 19:38)

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item