知识卡片
现实实验用于检验预测分布
将模型的干预预测与独立实验比较,可检验仅靠观察拟合难以检验的机制。有限样本不要求结果逐点相同,应比较预先定义的分布、目标量及不确定性范围;差异线索还需排查实施或测量是否与模型干预一致。
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
- · 干预与因果效应
原书出处 · 1 处
- · 查看原书依据
Suppose your causal model predicts the outcome of an intervention. You then do that intervention in the real world, such as with a controlled experiment. If your predicted intervention outcome conflicts with your actual intervention outcome, your causal model is wrong.
参考来源
- 位置:《Causal AI》第07章《干预与因果效应》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-7.xhtml)
- 结论依据:摘录中关于现实实验用于检验预测分布的定义、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:Suppose your causal model predicts the outcome of an intervention. You then do that intervention in the real world, such as with a controlled experiment. If your predicted intervention outcome conflicts with your actual intervention outcome, your causal model is wrong.