Covariance

Creator
Creator
Seonglae Cho
Created
Created
2023 Mar 7 2:38
Editor
Edited
Edited
2024 Oct 28 0:7
Refs

Dispersion matrix

A measure of
Linearity
relationship

Variance
is for 1-dimensional data while
Covariance Matrix
is for vector data distribution
Definition
cov(X,Y)=E[(XE[X])(YE[Y])]=E[XY]E[X]E[Y]cov(X, Y) = E[(X - E[X])(Y - E[Y])] \newline = E[XY] - E[X]E[Y]
using definition
V[X+Y]=E[(X+Y)2](E[X+Y])2=V[X]+V[Y]+Cov[X,Y]V[X+Y] = E[(X+Y)^2] - (E[X + Y])^2 \\ = V[X] + V[Y] + Cov[X, Y]
Pairwise Independence
Covariance
0, not reversal. But jointly normally distributed but uncorrelated, then they are indeed independent.
X와0 Y가 각각의 평균에서 떨어진 정도를 곱한 기대값이므로, 이를 두 벡터의 내적으로 해석할 수 있다. 특히
Correlation
은 cos 같이 -1 ~ 1로 바운딩된 형태로 벡터 크기 나눠준 것과 같음.
 
 
 
 

Recommendations