# 具有启发性的地方

2018-03-05 16:31:34

1. expected test MSE

use：to assess the accuracy of model predictions.

obtain: repeatedly estimate f using a large number of training sets and test each at x0.

decompose: into 3 parts -- variance, bias and irreducible error.

note: the meaning of variance and bias, the trade-off between variance and bias (geneally, more flexible methods result in higher variance and less bias).

2. 理解 the standard error of the mean (SEM)

1) 为什么要提出 SEM 的概念？

2) 一个 population 有自身的分布，因而有自身的 mean 和 variance。现在由于观测不到 population mean，用 sample mean 作为 population mean 的估计（样本统计量作为总体参数的估计值例子之一）。重复抽样并记录下多个 sample mean，这些 sample mean 形成了一个新的

...

1. expected test MSE

use：to assess the accuracy of model predictions.

obtain: repeatedly estimate f using a large number of training sets and test each at x0.

decompose: into 3 parts -- variance, bias and irreducible error.

note: the meaning of variance and bias, the trade-off between variance and bias (geneally, more flexible methods result in higher variance and less bias).

2. 理解 the standard error of the mean (SEM)

1) 为什么要提出 SEM 的概念？

2) 一个 population 有自身的分布，因而有自身的 mean 和 variance。现在由于观测不到 population mean，用 sample mean 作为 population mean 的估计（样本统计量作为总体参数的估计值例子之一）。重复抽样并记录下多个 sample mean，这些 sample mean 形成了一个新的分布，叫做 the sampling distribution of the population mean，这个分布又有自身的 mean 和 variance。

- 新分布的 mean 等于 population mean（unbiasedness）。

- 新分布的 variance 等于 population variance 除以样本容量n。

3. 解释 simple linear regression 和 multiple linear regression 结论中看似矛盾之处

simple linear regression 显示 sales 和 newspaper 显著相关，然而在 sales 对 newspaper、TV、radio 的 multiple linear regression 中，sales 和 newspaper 的相关关系却并不显著，如何解释这种矛盾？

===

2018/5/6 补充：

But in the case of a regression derivative, the conditional mean does not literally hold all else constant. It only holds constant the variables included in the conditional mean. This means that the regression derivative depends on which regressors are included. For example, in a regression of wages on education, experience, race and sex, the regression derivative with respect to education shows the marginal effect of education on mean wages, holding constant experience, race and sex. But it does not hold constant an individual’s unobservable characteristics (such as ability), nor variables not included in the regression (such as the quality of education).

4. 有了 t 检验为什么还需要 F 检验

5. 解释 simple logistic regression 和 multiple logistic regression 结论中看似矛盾之处

6. the overall error rate is not of interest

1
0