The Observation Theory EncyclopediaFrom TSKAboutBy kindBy chapterBy Lean fileLedgerProvenance

attribute type concept

DefinitionThe declaration of which transformations of a column keep its meaning, any injective relabelling for nominal, a strictly increasing map for ordinal, an affine map for interval, and a positive rescaling for ratio, nested in that order. Chapter 2 section 2.1. Also nominal, ordinal, interval scale, ratio scale.
ExampleTemperature in Celsius is an interval scale, so a ratio of two temperatures means nothing, while 4 metres is twice 2 metres on the ratio scale of length.
BookData Mining as Observation, draft 0.2, commit f3914f0; entry id attribute-type, kind concept.
Statusno ledger row names this entry. Corrections: none recorded.
Defining equationnone
Assumptions and scope
  • The declaration of which transformations of a column do not change its meaning. A ratio scale permits a positive rescaling, an interval scale an affine map with positive slope, an ordinal scale a strictly increasing map, and a nominal scale any injective relabelling, and the four classes are nested in that order.
  • A rescaling preserves ratios and an affine map preserves ratios of differences, so a consumer that reads a ratio of two interval-scale columns reads the origin the scale said was arbitrary.
Prior artnone recorded
Evidencelean/DataMiningAsObservation/AttributeType.lean
Reviewednot yet reviewed; generated 2026-09-10 from records at the commits on the provenance page.
ratiointervalordinalnominalrescale ⊂ affine ⊂ increasing ⊂ injective
The four scales and the transformations each permits, nested from ratio to nominal.

Equation

none

Conditions

Conditions are curated in entries.toml rather than read from a record.

Ledger

none

First stated

Stevens, on the theory of scales of measurement, 1946, as chapter 2 section 2.1 of Data Mining as Observation reads it after TSK section 2.1.

Measurements

Where the book states it Numbers, as the book’s sources table records them Source
chapter 2 section 2.1 the four attribute types and permitted transformations TSK 2e section 2.1

Failures and corrections

none

Invariance envelope

none declared

Machine checked

lean/DataMiningAsObservation/AttributeType.lean, theorems scale_affine, affine_strictMono, strictMono_injective, scale_preserves_ratio, affine_preserves_difference_ratio, at observation-data-mining f3914f0; what the check covers is stated in the book’s appendix C.

Used in

Data Mining as Observation chapters 2, 13.

Related

standardization; discretization; quotient.

See also

Book equations stated beside the entry’s terms, not defining it: 2.1, 0.12a.

Status

Generated 2026-09-10 by encyclopedia/generate.py; book at observation-data-mining f3914f0; the commit of every record is listed in the encyclopedia’s provenance.

← attentionattribution →