{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

solutions09

# solutions09 - Stat 351 Fall 2007 Assignment#9 Solutions 1(a...

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

Stat 351 Fall 2007 Assignment #9 Solutions 1. (a) By Definition I, we see that X 1 - ρX 2 is normally distributed with mean E ( X 1 - ρX 2 ) = E ( X 1 ) - ρE ( X 2 ) = 0 and variance var( X 1 - ρX 2 ) = var( X 1 ) + ρ 2 var( X 2 ) - 2 ρ cov( X 1 , X 2 ) = 1 + ρ 2 - 2 ρ 2 = 1 - ρ 2 . That is, X 1 - ρX 2 = Y where Y N (0 , 1 - ρ 2 ). Hence, Y = 1 - ρ 2 Z where Z N (0 , 1). In other words, there exists a Z N (0 , 1) such that X 1 - ρX 2 = 1 - ρ 2 Z. 1. (b) Since X = ( X 1 , X 2 ) is MVN, and since Z = X 1 1 - ρ 2 - ρX 2 1 - ρ 2 , we conclude that ( Z, X 2 ) is also a MVN. Hence, we know from Theorem V.7.1 that the components of a MVN are independent if and only if they are uncorrelated. We find cov( Z, X 2 ) = cov X 1 1 - ρ 2 - ρX 2 1 - ρ 2 , X 2 = 1 1 - ρ 2 cov( X 1 , X 2 ) - ρ 1 - ρ 2 var( X 2 ) = ρ 1 - ρ 2 - ρ 1 - ρ 2 = 0 which verifies that Z and X 2 are, in fact, independent. Exercise 4.2, page 127 : If φ ( t, u ) = exp { it - 2 t 2 - u 2 - tu } = exp { it - 1 2 (4 t 2 + 2 tu + 2 u 2 ) } , then we recognize this as the characteristic function of a normal random variable X = ( X 1 , X 2 ) N 1 0 , 4 1 1 2 .

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.

{[ snackBarMessage ]}