Heesen, Remco (2013) How Much Evidence Should One Collect? [Preprint]

Preview

PDF Bernoulli_paper_(Oct_10_2013_version_sent_to_Kevin).pdf - Draft Version Download (302kB)

Abstract

This paper focuses on the question how much evidence one should collect before deciding on the truth-value of a proposition. An analysis is given of a model where evidence takes the form of Bernoulli-distributed random variables. From a Bayesian perspective, the optimal strategy depends on the potential loss of drawing the wrong conclusion about the proposition and the cost of collecting evidence. It turns out to be best to collect only small amounts of evidence unless the potential loss is very large relative to the cost of collecting evidence.

---

Export/Citation:

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

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Heesen, Remco rheesen@andrew.cmu.edu
Keywords:	Bayesian epistemology, philosophy of science, evidence, sequential probability-ratio test, formal epistemology
Subjects:	General Issues > Decision Theory General Issues > Experimentation
Depositing User:	Remco Heesen
Date Deposited:	27 Oct 2013 12:01
Last Modified:	17 Nov 2015 03:19
Item ID:	10065
Subjects:	General Issues > Decision Theory General Issues > Experimentation
Date:	10 October 2013
URI:	https://philsci-archive.pitt.edu/id/eprint/10065

Available Versions of this Item

• How Much Evidence Should One Collect? (deposited 27 Oct 2013 12:01) [Currently Displayed]
  • How Much Evidence Should One Collect? (deposited 17 Nov 2015 03:19)

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item