矩
定义:
设 X X X是随机变量,如果
E ( X k ) , k = 1 , 2 , ⋯ E(X^{k}),k=1,2,\cdots E(Xk),k=1,2,⋯
存在,则称之为 X X X的 k k k阶原点矩
设 X X X是随机变量,如果
E { [ X − E ( X ) ] k } , k = 1 , 2 , 3 , ⋯ E \left\{[X-E(X)]^{k}\right\},k=1,2,3,\cdots E{
[X−E(X)]k},k=1,2,3,⋯
存在,则称之为 X X X的 k k k阶中心矩
设 X X X和 Y Y Y是两个随机变量,如果
E ( X k Y l ) , k , l = 1 , 2 , ⋯ E(X^{k}Y^{l}),k,l=1,2,\cdots E(XkYl),k,l=1,2,⋯
存在,则称之为 X X X和 Y Y Y的 k + l k+l k+l阶混合矩
设 X X X和 Y Y Y是两个随机变量,如果
E { [ X − E ( X ) ] k [ Y − E ( Y ) ] l } , k , l = 1 , 2 , ⋯ E \left\{[X-E(X)]^{k}[Y-E(Y)]^{l}\right\},k,l=1,2,\cdots E{
[X−E(X)]k[Y−E(Y)]l},k,l=1,2,⋯
存在,则称之为 X X X和 Y Y Y的 k + l k+l k+l阶混合中心矩
协方差
定义:对于随机变量 X X X和 Y Y Y,如果 E { [ X − E ( X ) ] [ Y − E ( Y ) ] } E \left\{[X-E(X)][Y-E(Y)]\right\} E{
[X−E(X)][Y−E(Y)]}存在,则称之为 X X X和 Y Y Y的协方差,记作 cov ( X , Y ) \text{cov}(X,Y) cov(X,Y),即
cov ( X , Y ) = E { [ X − E ( X ) ] [ Y − E ( Y ) ] } \text{cov}(X,Y)=E \left\{[X-E(X)][Y-E(Y)]\right\} cov(X,Y)=E{
[X−E(X)][Y−E(Y)]}
计算公式
- cov ( X , Y ) = E ( X Y ) − E ( X ) E ( Y ) \text{cov}(X,Y)=E(XY)-E(X)E(Y) cov(X,Y)=E(XY)−E(X)E(Y)
- D ( X ± Y ) = D ( X ) + D ( Y ) ± cov ( X , Y ) D(X \pm Y)=D(X)+D(Y)\pm \text{cov}(X,Y) D(X±Y)=D(X)+D(Y)±cov(X,Y)
性质
- cov ( X , Y ) = cov ( X , Y ) \text{cov}(X,Y)=\text{cov}(X,Y) cov(X,Y)=cov(X,Y)
- cov ( a X , b Y ) = a b cov ( X , Y ) \text{cov}(aX,bY)=ab \text{cov}(X,Y) cov(aX,bY)=abcov(X,Y),其中 a , b a,b a,b是常数
- cov ( X 1 + X 2 , Y ) = cov ( X 1 , Y ) + cov ( X 2 , Y ) \text{cov}(X_{1}+X_{2},Y)=\text{cov}(X_{1},Y)+\text{cov}(X_{2},Y) cov(X1+X2,Y)=cov(X1,Y)+cov(X2,Y)
例1:设随机变量 X 1 , X 2 , ⋯ , X n ( n > 1 ) X_{1},X_{2},\cdots ,X_{n}(n>1) X1,X2,⋯,Xn(n>1)相互独立,均服从正态分布 N ( 0 , σ 2 ) N(0,\sigma^{2}) N(0,σ2),则 cov ( X 1 , 1 n ∑ i = 1 n X i ) = ( ) \text{cov}(X_{1}, \frac{1}{n}\sum\limits_{i=1 }^{n}X_{i})=() cov(X1,n1i=1∑nXi)=()
注意此处 1 n ∑ i = 1 n X i ≠ E ( X ) \begin{aligned} \frac{1}{n}\sum\limits_{i=1}^{n}X_{i}\ne E(X)\end{aligned} n1i=1∑nXi=E(X)
cov ( X 1 , 1 n ∑ i = 1 n X i ) = E ( X 1 − E X 1 ) ( 1 n ∑ i = 1 n X i − 1 n ∑ i = 1 n E X i ) = E [ X 1 ( 1 n ∑ i = 1 n X i ) ] = 1 n E ( X 1 ∑ i = 1 n X i ) = 1 n E ( X 1 2 + ∑ i = 2 n X 1 X i ) = 1 n ( σ 2 + ∑ i = 2 n 0 ) = σ 2 n \begin{aligned} \text{cov}(X_{1},\frac{1}{n}\sum\limits_{i=1}^{n}X_{i})&=E(X_{1}-EX_{1})(\frac{1}{n}\sum\limits_{i=1}^{n}X_{i}- \frac{1}{n}\sum\limits_{i=1}^{n}EX_{i})\\ &=E\left[X_{1} \left(\frac{1}{n}\sum\limits_{i=1}^{n}X_{i}\right) \right]\\ &=\frac{1}{n}E(X_{1}\sum\limits_{i=1}^{n}X_{i})\\ &=\frac{1}{n}E(X_{1}^{2}+\sum\limits_{i=2}^{n}X_{1}X_{i})\\ &=\frac{1}{n}(\sigma^{2}+\sum\limits_{i=2}^{n}0)\\ &=\frac{\sigma^{2}}{n} \end{aligned} cov(X1,n1i=1∑nXi)=E(X1−EX1)(n1i=1∑nXi−n1i=1∑nEXi)=E[X1(n1i=1∑nXi)]=n1E(X1i=1∑nXi)=n1E(X12+i=2∑nX1Xi)=n1(σ2+i=2∑n0)=nσ2
例2:箱中装有 6 6 6个球,其中红、白、黑球的个数分别为 1 , 2 , 3 1,2,3 1,2,3个,现从箱中随机地取出 2 2 2个球,记 X X X为取出红球的个数, Y Y Y为取出的白球个数,求 cov ( X , Y ) \text{cov}(X,Y) cov(X,Y)
X X X |
---|