Measured Inference

Scales, Statistics, and Scientific Inference

Bibliographic Data

ID10705698
AuthorsConor Mayo-Wilson (University of Washington), Conor Mayo‐Wilson (University of Washington, corresponding author)
Year2025
Volume92
Issue5
Pages1-13
Publication date2025-09-04
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenuePhilosophy of Science (JOURNAL)
Journal identifiersISSN: 0031-8248 • E-ISSN: 1539-767X
PublisherCambridge University Press (CUP) (PUBLISHER)
DOI10.1017/psa.2025.10173
OpenAlexW4414000019
LanguageEN
References cited10

Despite the recent “epistemic turn” in the philosophy of measurement, philosophers have ignored a nearly 80 year controversy about the relationship between statistical inference and measurement theory. Some scholars maintain that measurement theory places no constraints on statistics, whereas others argue that the measurement scale (e.g., ordinal or interval) of one’s data determines which statistical methods are “permissible.” I defend an intermediate position: even if existing measurement theory were irrelevant to statistical inference, it would be critical for scientific inference, which requires connecting statistical hypotheses to broader research hypotheses

Bayesian inference · Bayesian probability · Econometrics · Fiducial inference · Frequentist inference · Inference · Predictive inference · Statistical inference · Statistics · Artificial Intelligence · Computer Science · Mathematics · Statistics Education and Methodologies

Tools

Open DOIOpen Access