定理2.4

定理2.4

简单随机样本的方差

$s^2=\frac{1}{n-1}\sum _{i=1}^n(y_i-\bar{y}{)}^2$

是总体方差$S^2$的无偏估计

证明：

对于总体中每个单元$Y_i$,引入示性变量$a_i$
$$a_i=\{\begin{array}{ll}1& \text{若}{Y}_i\text{入样}\\ 0& \text{若}{Y}_i\text{不入样}\end{array}$$

$$\begin{array}{rl}E(s^2)& =E\left(\frac{1}{n-1}\sum _{i=1}^n(y_i-\bar{y}{)}^2\right)\\ & =\frac{1}{n-1}E\left(\sum _{i=1}^n(y_i-\bar{y}{)}^2\right)\\ & =\frac{1}{n-1}E\left(\sum _{i=1}^n{y}_i^2-n{\bar{y}}^2\right)\\ & =\frac{1}{n-1}\left[E\left(\sum _{i=1}^n{y}_i^2\right)-E(n{\bar{y}}^2)\right]\\ & =\frac{1}{n-1}\left[E\left(\sum _{i=1}^N{Y}_i^2{a}_i\right)-nE({\bar{y}}^2)\right]\\ & =\frac{1}{n-1}\left[E(a_i)\sum _{i=1}^N{Y}_i^2-nV(\bar{y})-n(E(\bar{y}){)}^2\right]\\ & =\frac{1}{n-1}\left(\frac{n}{N}\sum _{i=1}^N{Y}_i^2-n\cdot \frac{1-f}{n}{S}^2-n{\bar{Y}}^2\right)\\ & =\frac{1}{n-1}\left(\frac{n}{N}\sum _{i=1}^N{Y}_i^2-\left(1-\frac{n}{N}\right)S^2-\frac{n}{N}\cdot N{\bar{Y}}^2\right)\\ & =\frac{1}{n-1}\left(\frac{n}{N}\left(\sum _{i=1}^N{Y}_i^2-N{\bar{Y}}^2\right)-\left(1-\frac{n}{N}\right)S^2\right)\\ & =\frac{1}{n-1}\left(\frac{n(N-1)}{N}{S}^2-\frac{N-n}{N}{S}^2\right)\\ & =\frac{1}{n-1}\cdot \frac{(n-1)N}{N}\cdot S^2\\ & =S^2\end{array}$$