Unverified50% confidenceFactExact time
The Matthews Correlation Coefficient (MCC) takes into account true positives, true negatives, false positives, and false negatives, with a value range of [-1, 1], and is more robust to class imbalance problems than accuracy.
1
Sources
50%
Confidence
Long-term
Relevance
9/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Matthews Correlation Coefficient (MCC) ranges from -1 to +1, where +1 indicates perfect prediction, 0 indicates random guessing, and -1 indicates completely inverse prediction75% similarUnverifiedMcNemar检验的零假设是b和c在总体中相等，即两个模型犯错方向对称，无系统性优劣68% similarUnverifiedMcNemar 检验关注两个模型在每个样本上的分歧情况，只有判断结果不一致的样本（b和c单元格）具有信息量，两者都对或都错的样本被视为无关信息67% similarUnverified评估基准测试质量的关键指标是假阳性率和假阴性率，理想基准应将两者控制在较低水平66% similarUnverified多重比较问题指同时测试多个模型变体时，即使每个单独检验显著性水平设为0.05，整体假阳性率也会急剧膨胀66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924660API
curl https://kongchang.com/api/v1/knowledge/claims/924660MCP
get_claim(id=924660)