Skip to main content

COMPEL Glossary / bias-relevant-variable

Bias-relevant variable

A feature whose inclusion, exclusion, or proxy-behavior affects fairness across protected groups — a direct sensitive attribute (race, gender) or an indirect proxy (postal code, device type).

What this means in practice

Identifying bias-relevant variables is a data-readiness activity because data selection decisions propagate into every downstream model.

Synonyms

sensitive variable , proxy variable

See also

  • Subgroup coverage — The representation of protected or intersectional groups in a dataset relative to their prevalence in the target population.
  • Data quality dimension — A measurable attribute of data integrity — accuracy, completeness, consistency, timeliness, validity, uniqueness, representativeness — used as a scoring axis in a data-readiness rubric.

Related articles in the Body of Knowledge