Module 2.4.1 · Phase 2 Decision · Step 2.4 Metrics & ThresholdsCore
Fairness Measurement Design
What do we measure, and what counts as good enough?
Turns your fairness definition into a measurement plan: what you measure, how you slice it and what counts as good enough.
What it does
You pick metrics through a decision tree and set thresholds, the subgroups and intersections to report, and the validation methods. Later modules such as Robustness Testing, Interventions Validation and CI/CD Integration read the plan.
Why it matters
This step translates fairness definitions into a binding measurement design, specifying metrics, thresholds, disaggregation requirements, and statistical validation criteria. It ensures that fairness evaluation is consistent, reproducible, and methodologically defensible.
Where it sits
- Fairness Definition
- Populations & Intersections
- Bias Identification & Prioritization
- Metrics & Thresholds
- Fairness Measurement Design
- Robustness Testing
- LLM Evidence Record
How to use it
In the Fairness Navigator Beta
Work through the steps in order. Several modules open from the Navigator's steps and hand their results back.
On its own Live
Open 2.4.1 from the platform's Modules page and run it when your project needs it. Work is saved with the assessment.
After a Pulse reading Live
Start with a fast first read, then go deeper with the modules where it points.