Auto-sync: 2026-04-21 00:02

This commit is contained in:
2026-04-21 00:02:55 +08:00
parent 177469a1cd
commit cb7c11e14f
235 changed files with 16567 additions and 237 deletions

View File

@@ -0,0 +1,24 @@
---
title: "Calibration Testing"
type: concept
tags: [ml-ops, evaluation, calibration]
sources: [specialized-model-qa]
last_updated: 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]]