Indicators for estimation systems

What the clause says

For an estimation system the indicator reflects the measured error, the challenge age, the demographic spread and the resistance to presentation attacks. The framework points to measurement rather than assertion.

What it supplies to a comparison

This is the indicator type most exposed to a misleading headline. The comparison should report the distribution and the attack result, not only the average.

Evidence to keep

• The error distribution by age and group.
• The presentation attack test and the live capture conditions.

What the evidence looks like

For 6.2.2, the first artefact is The error distribution by age and group.. The second is The presentation attack test and the live capture conditions.. If 6.2.2 has no first artefact, the practice is unproven at 6.2.2, and the report should record the absence rather than infer the practice from a policy.

Questions for the provider

1. What is the worst-performing group, and how large is the gap?
2. Were the capture conditions the same as the deployment conditions?

How it connects to the draft

Indicators for estimation systems belongs to 6 indicators of confidence, and it gives the analysis one fixed point: This is the indicator type most exposed to a misleading headline. The comparison should report the distribution and the attack result, not only the av. A comparison that cannot place a result against 6.2.2 is measuring something the framework has not defined, and the report should say so.

In the register, 6.2.2 is read beside the unit that tests it, and where it sets an objective rather than a number, that unit turns the objective into a question and an evidence artefact.