期望值和方差
期望值的性質:
-
E[c]=c for any constant c.
-
E[ag(x)+b]=aE[g(X)]+b
-
g(x)≥0,∀x⟹E[g(X)]≥0
hence X≥Y⟹E[X]≥E[Y]
-
∣E[g(X)]∣≤E[∣g(X)∣]
-
r>0,E[∣g(X)∣r]<∞⟹E[∣g(X)∣s]<∞,∀0<s≤r
-
X⊥Y⟹g(X)⊥h(Y), and E[g(X)h(Y)]=E[g(X)]E[h(Y)]
Let X be a r.v. with E[X] exists, then ∀c
E[(X−c)2]=E[X−E[X]+E[X]−c]2=E[(X−E[X])2]+2E[(X−E[X])(E[X]−c)]+(E[X]−c)2=E[(X−E[X])2]+(E[X]−c)2
i.e. E[(X−c)2]≥E[(X−E[X])2], and the equality holds if and only if c=E[X].
也就是说 E[X] 是 X 的均值(中心),因为每个点到 E[X] 的距离的平方的期望值最小。
Variance
X 每个點 到中心的距离的平方的期望值,即 X 的分散程度,称为 X 的方差。
σ2(X)alsoVar(X)=E[(X−E[X])2]=E[X2]−(E[X])2≥0
方差的性質:
-
Var(c)=0
-
Var(ag(X)+b)=a2Var(g(X))
-
Var(X+Y)=E[(X+Y−E[X]−E[Y])2]=E[(X−E[X])2]+E[(Y−E[Y])2]+2E[(X−E[X])(Y−E[Y])]=Var(X)+Var(Y)+2Cov(X,Y)
with Cov(X,Y)≜E[(X−E[X])(Y−E[Y])]=E[XY]−E[X]E[Y] is called the covariance(共變數) of X and Y.
也就是說,當 X−E[X] 和 Y−E[Y] 同號時, Cov(X,Y)>0,異號時 Cov(X,Y)<0。
將 Cov 進行歸一化(unit-free)得到
Var(X)Var(Y)Cov(X,Y)≜ρX,Y
稱為 X 和 Y 的相關係數(correlation coefficient)。
如果 X⊥Y⟹E[XY]=E[X]E[Y]⟹Cov(X,Y)=0⟹ρX,Y=0 and Var(X+Y)=Var(X)+Var(Y)
動差(Moments)
The Moment Generation Function of X is defined as
MX(t)≜E[etX],t∈R
Facts:
- MX(0)=E[E0X]=E[1]=1
- If MX(t) exists ∀∣t∣<δ for some δ>0, then E[Xk] exists ∀k=1,2,⋯
and is given by E[Xk=MX(k)]∣t=0=MX(t)(0)
- XdY⟺MX(t)=MY(t)