def. Covariance. Covariance measures the joint variability of two R.V.s; let X,Y.
- When X,Y show similar behavior, Cov(X,Y)>0
- When X,Y show opposite behavior, Cov(X,Y)<0
Cov(X,Y):=E((X−μX)(Y−μY))=E(X⋅Y)−E(X)⋅E(Y)
- When X⊥Y, then Cov(X,Y)=0; but Cov(X,Y) does not imply X⊥Y
- Covariance is a generalization of Variance: Var(X)=E((X−μX)2)=Cov(X,X)
thm. Relationship between Covariance and Variance. let X,Y. then:
Var(X+Y)=Var(X)+Var(Y)−2⋅E((X−μX)(Y−μY))=Var(X)+Var(Y)−2Cov(X,Y)
- When X⊥Y then Var(X,Y)=Var(X)+Var(Y)
thm. Bilinearity of Covariance.
- Cov(aX,aY)=ab⋅Cov(X,Y)
- Cov(X,Y+Z)=Cov(X,Y)+Cov(X,Z)
thm. Summed Variance. let X1,…,Xn. Then
Var(i∑Xi)=i∑Var(Xi)+2∀j,k s.t.j<k∑Cov(Xj,Xk)
E.G. second summation has (23) terms:
Var(X1+X2+X3)=Var(X1)+Var(X2)+Var(X3)+2⋅Cov(X1,X2)+2⋅Cov(X2,X3)+2⋅Cov(X1,X3)