知识卡片
异方差要写进噪声缩放
若Y|X=x的标准差为√x,可用独立N~Normal(0,1)写成Y:=g(X)+√X·N,要求X>0时尺度有效。这里外生N独立,但扰动幅度随X变化,属于显式父噪声交互,不能继续称独立同分布的加性残差。
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
- · 结构因果模型
原书出处 · 1 处
- · 查看原书依据
This implementation did not represent the exogenous variable Ny explicitly, but statistics theory tells us that using the mean squared error loss function is equivalent to assuming Ny was additive and had a normal distribution. However, it also assumes that the normal distribution had constant variance, while the funnel shape in the scatterplot indicates the variance of Ny might increase with the value of X.
参考来源
- 位置:《Causal AI》第06章《结构因果模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-6.xhtml)
- 结论依据:摘录中关于异方差要写进噪声缩放的定义、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:This implementation did not represent the exogenous variable Ny explicitly, but statistics theory tells us that using the mean squared error loss function is equivalent to assuming Ny was additive and had a normal distribution. However, it also assumes that the normal distribution had constant variance, while the funnel shape in the scatterplot indicates the variance of Ny might increase with the value of X.