X 1 , ⋯ , X n ∼ iid N ( μ , σ 2 ) X_1,\cdots,X_n \sim \text{iid} N(\mu,\sigma^2) X1,⋯,Xn∼iidN(μ,σ2)
- X ˉ ∼ N ( μ , σ 2 n ) \bar X \sim N(\mu, \dfrac{\sigma^2}{n}) Xˉ∼N(μ,nσ2)
- ∑ i = 1 n ( X i − X ˉ ) 2 ∼ σ 2 χ 2 ( n − 1 ) \sum_{i=1}^n (X_i-\bar X)^2 \sim \sigma^2 \chi^2(n-1) ∑i=1n(Xi−Xˉ)2∼σ2χ2(n−1)
- X ˉ \bar X Xˉ和 ∑ i = 1 n ( X i − X ˉ ) 2 \sum_{i=1}^n (X_i-\bar X)^2 ∑i=1n(Xi−Xˉ)2相互独立
证明：
令
X
⃗
=
[
X
1
,
⋯
,
X
n
]
⊤
\vec X = [X_1,\cdots,X_n]^\top
X=[X1,⋯,Xn]⊤
构造正交矩阵
A
\mathbf A
A
A
=
[
1
n
⋯
1
n
⋯
⋯
⋯
]
A = \begin{bmatrix} \dfrac{1}{\sqrt n} & \cdots & \dfrac{1}{\sqrt n} \\ \cdots & \cdots & \cdots \end{bmatrix}
A=⎣⎡n1⋯⋯⋯n1⋯⎦⎤
满足
A
=
[
a
⃗
1
,
⋯
,
a
⃗
n
]
A=[\vec a_1, \cdots, \vec a_n]
A=[a1,⋯,an]，
a
⃗
1
+
⋯
+
a
⃗
n
=
[
n
,
0
,
⋯
,
0
]
⊤
\vec a_1 + \cdots + \vec a_n = [\sqrt n,0,\cdots,0]^\top
a1+⋯+an=[n,0,⋯,0]⊤
令
Y
⃗
=
A
X
⃗
\vec Y = \mathbf A \vec X
Y=AX
于是我们有
Y
2
,
⋯
,
Y
n
∼
iid
N
(
0
,
σ
2
)
Y_2,\cdots,Y_n \sim \text{iid} N(0,\sigma^2)
Y2,⋯,Yn∼iidN(0,σ2)
这时，
X
ˉ
=
1
n
Y
1
\bar X = \dfrac{1}{\sqrt n} Y_1
Xˉ=n1Y1
∑
i
=
1
n
(
X
i
−
X
ˉ
)
2
=
(
∑
i
=
1
n
X
i
2
)
−
n
X
ˉ
2
=
(
∑
i
=
1
n
Y
i
2
)
−
Y
1
2
=
∑
i
=
2
n
Y
i
2
∼
σ
2
χ
2
(
n
−
1
)
\begin{aligned} \sum_{i=1}^n (X_i-\bar X)^2 = & \left( \sum_{i=1}^n X_i^2 \right) - n \bar{X}^2 \\ = & \left( \sum_{i=1}^n Y_i^2 \right) - Y_1^2 \\ = & \sum_{i=2}^n Y_i^2 \sim \sigma^2 \chi^2(n-1) \end{aligned}
i=1∑n(Xi−Xˉ)2===(i=1∑nXi2)−nXˉ2(i=1∑nYi2)−Y12i=2∑nYi2∼σ2χ2(n−1)
由于
Y
1
,
⋯
,
Y
n
Y_1,\cdots,Y_n
Y1,⋯,Yn独立同分布，故
Y
1
Y_1
Y1和
∑
i
=
2
n
Y
i
2
\sum_{i=2}^n Y_i^2
∑i=2nYi2相互独立，故
X
ˉ
\bar X
Xˉ和
∑
i
=
1
n
(
X
i
−
X
ˉ
)
2
\sum_{i=1}^n (X_i-\bar X)^2
∑i=1n(Xi−Xˉ)2相互独立
297
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
