4.1Standard
A subgroup is small and its fairness metric varies widely.
Do not hide it in the overall average.
Choose two responses.
× Incorrect
Report sample size, confidence intervals, and label quality, and use additional data, stratified sampling, and human review rather than excluding the group.
Detailed explanation
CorrectShow sample size, confidence interval, and label quality
Uncertainty is not overstated.
CorrectUse additional data, stratified sampling, and human review to check impact
Measurement gaps and real harm are investigated.
IncorrectDeclare fairness from a point estimate alone
Sampling variation is ignored.
IncorrectExclude the subgroup because it is small
Its impact cannot be measured.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 4.1の公平性指標、不確実性、データ代表性を確認する。
Official references
What to confirm
小規模集団を除外せず、指標の不確実性と実影響を評価できる。
Key points
- Small group
- Confidence interval
- Additional data
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Confidence interval
A range expressing uncertainty around an estimated statistic.
Stratified sampling
Sampling that preserves or deliberately controls representation for defined groups.
Question IDAWS-AIF-286
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue