PhilSci Archive

Epistemic Reliability of Neyman-Pearson Hypothesis Testing and Its Pragmatic Value-Laden Unequal Error Risk Setting

Kubiak, Adam and Kawalec, Pawel and Kiersztyn, Adam (2020) Epistemic Reliability of Neyman-Pearson Hypothesis Testing and Its Pragmatic Value-Laden Unequal Error Risk Setting. [Preprint]

WarningThere is a more recent version of this item available.
[img]
Preview
Text
Epistemic Reliability of NP 20_08_2020.pdf

Download (671kB) | Preview

Abstract

In this paper, we examine whether N-P can be seen as principally satisfying, in a minimal sense, some general epistemic standards and how pragmatic value-laden uneven setting of error probabilities can influence it. Using the concept of predictive value it is shown that Neyman-Pearson's theory of testing hypothesis offers at least minimal epistemic reliability only under the assumption that among the tested hypotheses the number of true hypotheses is equal to the number of false hypotheses. We also argue that N-P does not protect from the possible negative effects of the pragmatic value-laden unequal setting of error probabilities on N-P’s epistemic reliability. We show how pragmatic factors implemented in the form of the asymmetric setting of probabilities of two types of error may have a positive or negative impact on the epistemic reliability of N-P dependent on the case of the hypothesis tested and the assumption about the ratio of true to false hypotheses. More importantly, we argue that in the case of negative impact no methodological adjustment is available to neutralize it so in such cases the discussed pragmatic-value-ladenness of N-P inevitably compromises the goal of attainment of the truth.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Kubiak, Adamadampkubiak@gmail.com0000-0001-7178-3784
Kawalec, Pawelpawel.kawalec@kul.pl0000-0001-7618-8298
Kiersztyn, Adamadam.kiersztyn.pl@gmail.com0000-0001-5222-8101
Keywords: frequentism; predictive value; statistical test; reliability; context; pragmatic values
Subjects: Specific Sciences > Probability/Statistics
General Issues > Values In Science
Depositing User: Adam Kubiak
Date Deposited: 22 Jul 2020 05:00
Last Modified: 22 Jul 2020 05:00
Item ID: 17597
Subjects: Specific Sciences > Probability/Statistics
General Issues > Values In Science
Date: 20 July 2020
URI: http://philsci-archive.pitt.edu/id/eprint/17597

Available Versions of this Item

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item