Lecture9

# Lecture9 - Ex: 2 ( x 2 + y 2 + x 2 y 2 + 1) Are x and y...

This preview shows pages 1–4. Sign up to view the full content.

•1 Lecture 9 Ex: Are x and y independent? First factor out as 22 2 2 2 1 (, ) (1 ) xy fx y xyx y π = ++ + xy f xy 2 2 1 [( 1 )( 1 ) ] xy y xyy = +++ ) 1 ( 1 ) 1 ( 1 2 2 x y + + = 11 () ) ) x f xd y yx ππ −∞ =⋅ ++ ) 1 ( 1 )) 2 ( 2 ( 1 ) 1 ( 1 | tan 1 ) 1 ( 1 2 2 1 2 x x y x + = + = + = Can similarly obtain => independent ) 1 ( 1 ) ( 2 y y f y + = () () xy x y f f xf y = 2 ) , ( R y x Independence Tests ± Graphical test of independence From previous discussion, x and y are independent then If we have equality for each y, then: Corollary: x and y are independent RV’s if Corollary: x and y are independent RV’s if (|) xx Fxy Fx = R y x , 12 (| ) Fxy = R y y x 2 1 , , f xy = R y y x 2 1 , ,

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

View Full Document
•2 Question: if we transform two independent RV’s by g(.) and h(.) , what can we say about g(x) and h(y)? ± Independence of functions of RV’s Theorem : Let x and y be two independent RV’s , let V=g(x) and W=h(y), then V and W are independent RV’s. ± Transformation of a Random vector: We distinguish 3 cases of interest: 1. One function of two RV’s : () Zx , y g = 2. Two functions of two RV’s: 3. More than two functions of two RV’s REMARK: It is important to note( in fact convince yourself) that uncorrelation does not imply independence. 11 zx , y g = 22 , y g = , y ii g = N i " , 1 = Example: Let(x,y) be a random two-tuple vector. The PDF of the vector is: X Y 1 4 3 2 (, ) xy f xy = 2 2 2 r y x C < + 2 2 2 0 r y x > + i.e. If x=0, y can take any value between –r and r with equal prob. If x=r, y can only be equal to zero. This clearly establishes the dependence between x and y . 2 1 r C π =
•3 If we now compute Hence establishing non-correlation of (x,y) while still dependent. ± Transformation of vectors: Ex: suppose we have , what is the PDF/distribution of Z when given () ( , ) xy x,y E xyf x y dxdy = ∫∫ 0 1 2 = = ∫∫ dxdy xy r C π zx , y g = (, ) XY f xy ( ) ( ( ) ) Z , y Gz P z Pg z = ≤= , y g = By computation : ( ( ) ) , y P zP g z (( ) ) x,y P D =∈ xy D f x y dxdy = X Z Y D Ex2: Z=XY Question: what is the distribution of such a transformation?

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 09/24/2009 for the course ECE 514 taught by Professor Krim during the Fall '08 term at N.C. State.

### Page1 / 10

Lecture9 - Ex: 2 ( x 2 + y 2 + x 2 y 2 + 1) Are x and y...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online