slides_4_ranvecs

# 62 independence and correlation if x and y are

This preview shows pages 62–72. Sign up to view the full content.

62

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Independence and Correlation If X and Y are independent random variables with E X 2 , E Y 2 then they are always uncorrelated: Cov X , Y 0. We already covered a more general version of this finding. In fact, for any functions g X and h Y , Cov g X , h Y  0. Why? Under independence we showed E g X h Y  E g X  E g Y  and so Cov g X , h Y  E g X h Y  E g X  E g Y  0 63
Independence is a much stronger requirement than uncorrelatedness. For example, suppose X has a symmetric distribution about its mean of zero. Let Y X 2 . Then X and Y are clearly not independent. For example, P Y 1,| X | 1 P X 2 1,| X | 1 P | X | 1 P X 2 1 P | X | 1 P Y 1 P | X | 1 unless P | X | 1 0 or 1. 64

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Interestingly, X and Y X 2 are uncorrelated: Cov X , X 2 E X X 2 E X 3 0 by symmetry. Even though Y is a deterministic function of X – once we know X , we always know Y Y is not linearly related to X . Correlation is often described as a measure of linear association. For many purposes it is suitable, but it can miss more complicated relationships. 65
As it turns out, if g X and h Y are uncorrelated for all functions g  and h  with finite second moments, then X and Y must be independent. This provides an idea of how much stronger independence between X and Y is compared with just saying X and Y are uncorrelated. 66

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Variance - Covariance Matrix Let X be an m 1 random vector with E X j 2 . We want to define the variance matrix of X , sometimes called the variance - covariance matrix of X or (less preferred) the covariance matrix of X . Let j 2 Var X j , j 1,2,..., m ij Cov X i , X j , i j so we have m (possibly) different variances and m m 1 /2 (possibly) distinct covariances. 67
Arrange these in an m m matrix and call this Var X : Var X 1 2 12 1 m 12 2 2 2 m 1 m 2 m m 2 Sometimes we write X Var X or even Var X . Note that ij ji has been imposed. This means that Var X is a symmetric matrix: X X . 68

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Often it is convenient to obtain Var X from a matrix expectation. Note that X X 1 1 X 2 2 X m m and so 69
X  X X 1 1 X 2 2 X m m X 1 1 X 2 2 X m m X 1 1 2 X 1 1  X m m X 1 1  X 2 2 X 2 2  X m m X 1 1  X m m X m m 2 70

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
It follows that Var X E  X 
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern