知识卡片
多次检验需整体错误控制
对一个图同时检验许多独立关系,会增加至少出现一次误报的机会。预先确定检验族、去重并选择适当的整体错误率或错误发现率控制,比把所有单次p值直接按同一阈值汇总更有解释力;校正后也不代表图已证实。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- · 查看原书依据
multiple comparisons problem. There are solutions to dealing with multiple comparisons problems, such as using false discovery rates. If you are familiar with such methods, applying them won’t hurt. If you want to learn more, see the chapter’s notes at https://www.altdeep.ai/p/causalaibook for references to false discovery rates in the context of causal modeling. But again, I encourage you to view traditional conditional independence testing as
参考来源
- 位置:《Causal AI》第04章《用因果约束检验DAG》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-4.xhtml)
- 结论依据:摘录中关于多次检验需整体错误控制的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:multiple comparisons problem. There are solutions to dealing with multiple comparisons problems, such as using false discovery rates. If you are familiar with such methods, applying them won’t hurt. If you want to learn more, see the chapter’s notes at https://www.altdeep.ai/p/causalaibook for references to false discovery rates in the context of causal modeling. But again, I encourage you to view traditional conditional independence testing as