covind - = 0) = P ( Y = 0 | X =-1) P ( X =-1) = 0 1 / 4 =...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Statistics 351 (Fall 2007) Covariance Zero Does Not Imply Independence The following exercise illustrates that two random variables can have covariance zero yet need not be independent. Exercise. Consider the random variable X defined by P ( X = - 1) = 1 / 4, P ( X = 0) = 1 / 2, P ( X = 1) = 1 / 4. Let the random variable Y be defined as Y := X 2 . Hence, P ( Y = 0 | X = 0) = 1, P ( Y = 1 | X = - 1) = 1, P ( Y = 1 | X = 1) = 1. Show that the density of Y is P ( Y = 0) = 1 / 2, P ( Y = 1) = 1 / 2. Find the joint density of ( X, Y ), and show that X and Y are not independent. Find the density of XY , compute E ( XY ), and show that X and Y are uncorrelated. Solution. We find the density of Y simply using the law of total probability : P ( Y = 0) = P ( Y = 0 | X = 1) P ( X = 1) + P ( Y = 0 | X = 0) P ( X = 0) + P ( Y = 0 | X = - 1) P ( X = - 1) = 0 · 1 / 4 + 1 · 1 / 2 + 0 · 1 / 4 = 1 / 2 , P ( Y = 1) = P ( Y = 1 | X = 1) P ( X = 1) + P ( Y = 1 | X = 0) P ( X = 0) + P ( Y = 1 | X = - 1) P ( X = - 1) = 1 · 1 / 4 + 0 · 1 / 2 + 1 · 1 / 4 = 1 / 2 . The joint density of ( X, Y ) is given by P ( X = 0 , Y = 0) = P ( Y = 0 | X = 0) P ( X = 0) = 1 · 1 / 2 = 1 / 2; P ( X = 0 , Y = 1) = P ( Y = 1 | X = 0) P ( X = 0) = 0 · 1 / 2 = 0; P ( X = 1 , Y = 0) = P ( Y = 0 | X = 1) P ( X = 1) = 0 · 1 / 4 = 0; P ( X = 1 , Y = 1) = P ( Y = 1 | X = 1) P ( X = 1) = 1 · 1 / 4 = 1 / 4; P ( X = - 1 , Y
Background image of page 1

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

View Full DocumentRight Arrow Icon
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: = 0) = P ( Y = 0 | X =-1) P ( X =-1) = 0 1 / 4 = 0; P ( X =-1 , Y = 1) = P ( Y = 1 | X =-1) P ( X =-1) = 1 1 / 4 = 1 / 4 . Since, for example, P ( X = 0 , Y = 0) = 1 / 2, but P ( X = 0) P ( Y = 0) = 1 / 2 1 / 2 = 1 / 4, we see that X and Y cannot be independent. The possible values of XY are 0, 1,-1. Hence, P ( XY = 0) = P ( X = 0 , Y = 0) = 1 / 2 and P ( XY = 1) = P ( X = 1 , Y = 1) = 1 / 4 using the computations above. By the law of total probability, P ( XY =-1) = 1 / 4 . (Equivalently, P ( XY =-1) = P ( X =-1 , Y = 1) = 1 / 4.) Thus, E ( XY ) = 0 P ( XY = 0) + 1 P ( XY = 1) + (-1) P ( XY =-1) = 0 + 1 / 4-1 / 4 = 0 . Since E ( X ) = 0 and E ( Y ) = 0, we see that Cov( X, Y ) = E ( XY )-E ( X ) E ( Y ) = 0-0 = 0; whence X and Y are uncorrelated....
View Full Document

This note was uploaded on 03/26/2012 for the course STAT 351 taught by Professor Michaelkozdron during the Fall '08 term at University of Regina.

Page1 / 2

covind - = 0) = P ( Y = 0 | X =-1) P ( X =-1) = 0 1 / 4 =...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online