# 1 n n 101 12n b therefore var s100 100 inequality

This preview shows page 1. Sign up to view the full content.

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

Unformatted text preview: ndom variable, Sr , with parameters r and p, arises as the sum of r independent geometrically distributed random variables with parameter r p. Each such geometric random variable has mean 1/p and variance (1 − p)/p2 . So, E [Sr ] = p and Var(Sr ) = r(1−p) . p2 . (c) Likewise, as seen in Section 3.5, a gamma random variable, Tr , with parameters r and λ, arises as the sum of r independent exponentially distributed random variables with parameter λ. An exponentially distributed random variable with parameter λ has mean 1/λ and variance 1/λ2 . r r Therefore, E [Tr ] = λ and Var(Tr ) = λ2 . 4.8. MOMENTS OF JOINTLY DISTRIBUTED RANDOM VARIABLES 153 Example 4.8.2 Simplify the following expressions: (a) Cov(8X + 3, 5Y − 2), (b) Cov(10X − 5, −3X + 15), (c) Cov(X+2,10X-3Y), (d) ρ10X,Y +4 . Solution (a) Cov(8X + 3, 5Y − 2) = Cov(8X, 5Y ) = 40Cov(X, Y ). (b) Cov(10X − 5, −3X + 15) = Cov(10X, −3X ) = −30Cov(X, X ) = −30Var(X ). (c) Cov(X+2,10X-3Y)=Cov(X,10X-3Y)=10Cov(X,X)-3Cov(X,Y)=10Var(X)-3Cov(X,Y). (d) Since Cov(10X, Y +4) = 10Co...
View Full Document

## This note was uploaded on 02/09/2014 for the course ISYE 2027 taught by Professor Zahrn during the Spring '08 term at Georgia Institute of Technology.

Ask a homework question - tutors are online