Glossary · Validity and evidence
Validity argument
4ValidationThe chain of claims behind an interpretation and use of a score: construct, representation, elicitation, scoring, generalization (task, seed, judge, environment, generator, time), and decision. Validity attaches to the argument, not a benchmark.
Also called: six claims, expanded validity argument
Defined in
Handbook · ValidationThe validity argumentValidity is a claim, not a sticker: a six-link argument from construct to decision, where any link can break.Related terms
- Validity
- The strength of evidence and theory supporting a particular interpretation and use of scores. Not a permanent property of a benchmark: validity is a claim, not a sticker.
- Construct validity
- The overall evidential argument that a measure behaves as expected for the target construct and not for competing explanations.
Where it comes up
- Task validity and outcome validityHandbook · Validation