Skip to content

Commit

Permalink
简单区分 standard error 与 standard deviation
Browse files Browse the repository at this point in the history
严格的讲,standard error (se) 与 standard deviation (sd) 是两个概念。The standard error is ... an estimate of that standard deviation (摘自 wikipedia). 可以简单理解为,sd是理论值,se是计算值,在实际计算中,se会无限逼近sd。
  • Loading branch information
jlh2018 authored Dec 3, 2018
1 parent 68f1d72 commit 8e3d8b8
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion Chapter5/machine_learning_basics.tex
Original file line number Diff line number Diff line change
Expand Up @@ -888,7 +888,7 @@ \subsection{方差和\glsentrytext{standard_error}}
\text{Var}(\hat{\theta})
\end{equation}
其中随机变量是训练集。
另外,方差的平方根被称为\firstgls{standard_error},记作$\text{SE}(\hat{\theta})$
另外,方差的平方根被称为\firstgls{standard_error}\footnote{~严格的讲,standard error (se) 与 standard deviation (sd) 是两个概念。The standard error is ... an estimate of that standard deviation (摘自 wikipedia). 可以简单理解为,sd是理论值,se是计算值,在实际计算中,se会无限逼近sd。},记作$\text{SE}(\hat{\theta})$

\gls{estimator:chap5}的方差或\gls{standard_error}告诉我们,当独立地从潜在的数据生成过程中重采样数据集时,如何期望估计的变化。
正如我们希望估计的偏差较小,我们也希望其方差较小。
Expand Down

0 comments on commit 8e3d8b8

Please sign in to comment.