Skip to content

Glossary · Reliability, calibration, and statistics

Reliability

4Validation

Stability of measurement across legitimate replications. Necessary but not sufficient: a perfectly repeatable evaluator can reliably measure the wrong construct.

Defined in

Handbook · ValidationReliability and generalizabilitySpecify what may legitimately vary, then measure how much tasks, seeds, judges and environments move the score.

Where it comes up

See it in the full glossary →