Unverified60% confidenceFactTime unknown
McNemar's test is a non-parametric test method specifically designed for paired binary classification data
2
Sources
60%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
Unverified该项目采用配对McNemar检验作为统计显著性验证方法79% similarUnverifiedMcNemar 检验要求两个模型在完全相同的测试集上评估，任何测试集的不一致都会使检验失效76% similarUnverified多种子实验中检验对象从单样本预测分歧变为多次运行的准确率序列时，通常已不再适用McNemar检验76% similarUnverified当比较两个具体训练模型的预测行为差异时应固定种子使用同一测试集运行McNemar检验，当评估方法整体优越性时应用多种子重复实验配合配对t检验或非参数检验72% similarUnverifiedR中的mcnemar.test()函数可以自动处理卡方近似与精确检验之间的切换71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/29805API
curl https://kongchang.com/api/v1/knowledge/claims/29805MCP
get_claim(id=29805)