I. S. Iwueze et al.
10.4236/am.2017.812136 1922 Applied Mathematics
2. Mean, Variance and Covariances of Powers of the Linear
Gaussian White Noise Process
2.1. Mean of Powers of the Linear Gaussian White Noise Process
Let
, where
is the linear Gaussian white noise
process. The expected value of
are needed for the
effective determination of the variance and covariance structure of
. Lemma
2.1 gives the required result.
Lemma 2.1: Let
be a linear Gaussian white noise process with
mean zero and variance
(
follows iid
), then
( )
( )
2
2 1 !!, 2 , 1, 2,
0, 2 1, 0,1,2,
m
d
t
m d mm
EX
dmm
σ
−==
=
=+=
(2.1)
where [16]
( ) ( ) ( )
1
21!!1357 21 21
m
k
m mk
=
− =×××× × − = −
∏
(2.2)
Proof:
Let
, then
(
)
2
2
2
2
1
e; ; 0
2
π
z
fz z
σ
σ
σ
−
= −∞< <∞ >
(2.3)
Note that
(2.4)
(2.5)
1) Case 1:
Equation (2.5) reduces to
( )
2
2
2
0
1
2 ed
2π
z
dd
EZ z z
σ
σ
−
∞
=
∫
(2.6)
Let
( )
1
2
22
2
2
22
2
z
y z yz y
σσ
σ
= ⇒ = ⇒=
( )
1111
2222
d 12 1
2
d 22
22
z
yyyy
y
σ
σ σσ
−−−−
= ⋅⋅ = = =
(2.7)
( )
1
2
1
2
2
0
1
2
2
0
2
2e d
2π 2
2
ed
π
m
dy
mm
m
y
y
EZ y y
yy
σ
σ
σ
σ
−
∞
−
−
∞
−
=
=
∫
∫
(2.8)