93 moment generating functions if x is an m 1 random

Info iconThis preview shows pages 93–103. Sign up to view the full content.

View Full Document Right Arrow Icon
93
Background image of page 93

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

View Full Document Right Arrow Icon
Moment Generating Functions If X is an m 1 random vector, we can define its moment generating function from m to 0, . For m 1 vectors t , X t E exp t X  The MGF is useful only insofar it is finite for t in a neighborhood of zero. But now we need to define the neighborhood using a distance measure in m . This is usually done using Euclidean length. 94
Background image of page 94
For an m 1 vector u , its Euclidean length, denote u ,isthe nonnegative number u ‖ j 1 m u j 2 1/2 The Euclidean distance between two vectors is t u ‖ j 1 m t j u j 2 1/2 95
Background image of page 95

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

View Full Document Right Arrow Icon
An open neighborhood around zero with radius 0 is defined as N 0 u m : u ‖  So, for the MGF to be useful, we must assume that there exists 0 such that X t E exp t X  for all t N 0 . 96
Background image of page 96
As in the scalar case, we can use the MGF to find moments of the random vector X . In particular X t 0 t X 0 E X X 2 t t 0 t 2 X 0 E XX 97
Background image of page 97

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

View Full Document Right Arrow Icon
We can then compute Var X E XX E X E X If the MGF of X is finite in a neighborhood of zero then it is easy to see that each X j has a finite MGF on an interval about zero. Denote these 1 , 2 ,..., m . We can always write X t E exp t X  E exp j 1 m t j X j E j 1 m exp t j X j by a key property of exp  . 98
Background image of page 98
If we now assume X 1 , X 2 ,..., X m are independent then E j 1 m exp t j X j j 1 m E exp t j X j  j 1 m j t j , that is X t X t 1 , t 2 t m j 1 m j t j . 99
Background image of page 99

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

View Full Document Right Arrow Icon
There is a converse to this statement, too. Namely, if for t j j , j for j 0 we can show X t j 1 m j t j , then X 1 , X 2 ,..., X m are independent. The MGF is particularly convenient for establishing facts about the multivariate normal distribution. 100
Background image of page 100
There also is an important relationship between the MGF of a sum and the MGFs of the summands when the summands are independent. Let X 1 , X 2 ,..., X m be independent random variables with MGFs j . Define Y X 1 X 2 ... X m . Y inherits its distribution from that of the random vector X .Ifthe X j are independent, that distribution is often much easier to characterize using the MGF of Y . This is because Y t X 1 X 2 ... X m t j 1 m j t 101
Background image of page 101

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

View Full Document Right Arrow Icon
Proof : We again use a key property of exp  along with independence: Y t E exp tY  E exp t X 1 ...
Background image of page 102
Image of page 103
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page93 / 107

93 Moment Generating Functions If X is an m 1 random vector...

This preview shows document pages 93 - 103. Sign up to view the full document.

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