定理2.3
对于简单随机抽样，有
C o v ( y ˉ , x ˉ ) = 1 − f n S y x Cov(\bar{y},\bar{x})=\frac{1-f}{n}S_{yx} Cov(yˉ,xˉ)=n1−fSyx
式中， S y x = 1 N − 1 ∑ i = 1 N ( Y i − Y ˉ ) ( X i − X ˉ ) S_{yx}=\frac{1}{N-1}\displaystyle\sum^{N}_{i=1}{(Y_i-\bar{Y})(X_i-\bar{X})} Syx=N−11i=1∑N(Yi−Yˉ)(Xi−Xˉ)为总体协方差
证明：
根据方差的性质可知：
V ( x ˉ + y ˉ ) = V ( x ˉ ) + V ( y ˉ ) + 2 C o v ( x ˉ , y ˉ ) = = > C o v ( x ˉ , y ˉ ) = 1 2 ( V ( x ˉ + y ˉ ) − V ( x ˉ ) − V ( y ˉ ) ) V(\bar{x}+\bar{y})=V(\bar{x})+V(\bar{y})+2Cov(\bar{x},\bar{y})\quad==>\quad Cov(\bar{x},\bar{y})=\frac{1}{2}\left(V(\bar{x}+\bar{y})-V(\bar{x})-V(\bar{y})\right) V(xˉ+yˉ)=V(xˉ)+V(yˉ)+2Cov(xˉ,yˉ)==>Cov(xˉ,yˉ)=21(V(xˉ+yˉ)−V(xˉ)−V(yˉ))
记
u
ˉ
=
x
ˉ
+
y
ˉ
,
U
ˉ
=
X
ˉ
+
Y
ˉ
\bar{u}=\bar{x}+\bar{y},\quad \bar{U}=\bar{X}+\bar{Y}
uˉ=xˉ+yˉ,Uˉ=Xˉ+Yˉ，则：
C
o
v
(
y
ˉ
,
x
ˉ
)
=
1
2
(
V
(
u
ˉ
)
−
V
(
x
ˉ
)
−
V
(
y
ˉ
)
)
=
1
2
(
1
−
f
n
S
u
2
−
1
−
f
n
S
x
2
−
1
−
f
n
S
y
2
)
=
1
−
f
2
n
(
S
u
2
−
S
x
2
−
S
y
2
)
=
1
−
f
2
n
(
1
N
−
1
∑
i
=
1
N
(
U
i
−
U
ˉ
)
2
−
1
N
−
1
∑
i
=
1
N
(
X
i
−
X
ˉ
)
2
−
1
N
−
1
∑
i
=
1
N
(
Y
i
−
Y
ˉ
)
2
)
=
1
−
f
2
n
⋅
1
N
−
1
(
∑
i
=
1
N
(
U
i
−
U
ˉ
)
2
−
∑
i
=
1
N
(
X
i
−
X
ˉ
)
2
−
∑
i
=
1
N
(
Y
i
−
Y
ˉ
)
2
)
=
1
−
f
2
n
⋅
1
N
−
1
(
∑
i
=
1
N
(
X
i
+
Y
i
−
X
ˉ
−
Y
ˉ
)
2
−
∑
i
=
1
N
(
X
i
−
X
ˉ
)
2
−
∑
i
=
1
N
(
Y
i
−
Y
ˉ
)
2
)
=
1
−
f
2
n
⋅
1
N
−
1
∑
i
=
1
N
[
(
(
X
i
−
X
ˉ
)
−
(
Y
i
−
Y
ˉ
)
)
2
−
(
X
i
−
X
ˉ
)
2
−
(
Y
i
−
Y
ˉ
)
2
]
=
1
−
f
2
n
⋅
1
N
−
1
∑
i
=
1
N
[
(
X
i
−
X
ˉ
)
2
+
2
(
X
i
−
X
ˉ
)
(
Y
i
−
Y
ˉ
)
+
(
Y
i
−
Y
ˉ
)
2
−
(
X
i
−
X
ˉ
)
2
−
(
Y
i
−
Y
ˉ
)
2
]
=
1
−
f
2
n
⋅
2
N
−
1
∑
i
=
1
N
(
X
i
−
X
ˉ
)
(
Y
i
−
Y
ˉ
)
=
1
−
f
2
n
S
y
x
\begin{aligned} Cov(\bar{y},\bar{x})&=\frac{1}{2}\left(V(\bar{u})-V(\bar{x})-V(\bar{y})\right)\\ &=\frac{1}{2}\left(\frac{1-f}{n}S_u^2-\frac{1-f}{n}S_x^2-\frac{1-f}{n}S_y^2\right)\\ &=\frac{1-f}{2n}\left(S_u^2-S_x^2-S_y^2\right)\\ &=\frac{1-f}{2n}\left(\frac{1}{N-1}\displaystyle\sum^{N}_{i=1}{(U_i-\bar{U})^2}-\frac{1}{N-1}\displaystyle\sum^{N}_{i=1}{(X_i-\bar{X})^2}-\frac{1}{N-1}\displaystyle\sum^{N}_{i=1}{(Y_i-\bar{Y})^2}\right)\\ &=\frac{1-f}{2n}·\frac{1}{N-1}\left(\displaystyle\sum^{N}_{i=1}{(U_i-\bar{U})^2}-\displaystyle\sum^{N}_{i=1}{(X_i-\bar{X})^2}-\displaystyle\sum^{N}_{i=1}{(Y_i-\bar{Y})^2}\right)\\ &=\frac{1-f}{2n}·\frac{1}{N-1}\left(\displaystyle\sum^{N}_{i=1}{(X_i+Y_i-\bar{X}-\bar{Y})^2}-\displaystyle\sum^{N}_{i=1}{(X_i-\bar{X})^2}-\displaystyle\sum^{N}_{i=1}{(Y_i-\bar{Y})^2}\right)\\ &=\frac{1-f}{2n}·\frac{1}{N-1}\displaystyle\sum^{N}_{i=1}{\left[((X_i-\bar{X})-(Y_i-\bar{Y}))^2-(X_i-\bar{X})^2-(Y_i-\bar{Y})^2\right]}\\ &=\frac{1-f}{2n}·\frac{1}{N-1}\displaystyle\sum^{N}_{i=1}{\left[(X_i-\bar{X})^2+2(X_i-\bar{X})(Y_i-\bar{Y})+(Y_i-\bar{Y})^2-(X_i-\bar{X})^2-(Y_i-\bar{Y})^2\right]}\\ &=\frac{1-f}{2n}·\frac{2}{N-1}\displaystyle\sum^{N}_{i=1}{(X_i-\bar{X})(Y_i-\bar{Y})}\\ &=\frac{1-f}{2n}S_{yx} \end{aligned}
Cov(yˉ,xˉ)=21(V(uˉ)−V(xˉ)−V(yˉ))=21(n1−fSu2−n1−fSx2−n1−fSy2)=2n1−f(Su2−Sx2−Sy2)=2n1−f(N−11i=1∑N(Ui−Uˉ)2−N−11i=1∑N(Xi−Xˉ)2−N−11i=1∑N(Yi−Yˉ)2)=2n1−f⋅N−11(i=1∑N(Ui−Uˉ)2−i=1∑N(Xi−Xˉ)2−i=1∑N(Yi−Yˉ)2)=2n1−f⋅N−11(i=1∑N(Xi+Yi−Xˉ−Yˉ)2−i=1∑N(Xi−Xˉ)2−i=1∑N(Yi−Yˉ)2)=2n1−f⋅N−11i=1∑N[((Xi−Xˉ)−(Yi−Yˉ))2−(Xi−Xˉ)2−(Yi−Yˉ)2]=2n1−f⋅N−11i=1∑N[(Xi−Xˉ)2+2(Xi−Xˉ)(Yi−Yˉ)+(Yi−Yˉ)2−(Xi−Xˉ)2−(Yi−Yˉ)2]=2n1−f⋅N−12i=1∑N(Xi−Xˉ)(Yi−Yˉ)=2n1−fSyx
扫一扫
1920
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
