nexus/wiki/concepts/Calibration-Testing.md

title, type, tags, sources, last_updated

title	type	tags	sources	last_updated
Calibration Testing	concept	ml-ops evaluation calibration	specialized-model-qa	2026-04-20

Definition

校准测试用于评估模型预测概率是否与真实发生率一致。

Common Methods

• Hosmer-Lemeshow test
• Brier score
• Reliability diagrams

Use in Model QA

• 检查概率输出是否可信
• 比较不同子群体的校准差异
• 评估分布漂移下的概率稳定性

Related Concepts

• Model Audit
• Discrimination Metrics