Digital Signal Processing Reference
In-Depth Information
A density function is obtained as the derivation of the corresponding distribution
function,
f
X
1
ðx
1
; t
1
Þ¼
@
F
X
1
ð
x
1
;
t
1
Þ
@x
1
P
f
x
1
<
X
1
x
1
þ
d
x
1
;
t
1
g
d
x
1
¼
:
(6.3)
The density function (
6.3
) is called a
density function of the first order
,ora
one-dimensional density.
6.2.2 Description of a Process in Two Points
Next we observe a process in two points denoted as
t
1
and
t
2
. The corresponding
random variables are
X
1
and
X
2
.A
joint distribution function
,a
second order
distribution
,ora
two-dimensional distribution
is defined as:
F
X
1
X
2
ðx
1
; x
2
;
t
1
; t
2
Þ¼PXðt
1
Þx
1
; Xðt
2
Þx
2
f g
¼ PfX
1
x
1
; X
2
x
2
;
t
1
; t
2
g:
(6.4)
Note again that this is the same definition as that of a joint distribution of two
random variables with only exception being that now the joint distribution depends
on time instants
t
1
and
t
2
.
The meaning of this distribution can also be interpreted using a frequency ratio, as
shown in Fig.
6.5
. Consider a total number of outcomes for which the corresponding
realizations are not more than
x
1
in a given time instant
t
1
and also not more than
x
2
in
a given time instant
t
2
. The obtained number is denoted as
n
(
x
1
,
x
2
,
t
1
,
t
2
). Then,
assuming a large
n
, a distribution function can be expressed as:
n
ð
x
1
;
x
2
;
t
1
;
t
2
Þ
n
F
X
1
X
2
ðx
1
; x
2
;
t
1
; t
2
Þ¼PfX
1
x
1
; X
2
x
2
;
t
1
; t
2
g
:
(6.5)
The corresponding density function is given as:
2
F
X
1
X
2
ð
x
1
;
x
2
;
t
1
;
t
2
Þ
@x
1
@x
2
f
X
1
X
2
ðx
1
; x
2
;
t
1
; t
2
Þ¼
@
Px
1
<
X
ð
t
1
Þ
x
1
þ
d
x
1
;
x
2
<
X
ð
t
2
Þ
x
2
þ
d
x
2
;
t
1
;
t
2
f
g
¼
d
x
1
d
x
2
P
f
x
1
<
X
1
x
1
þ
d
x
1
;
x
2
<
X
2
x
2
þ
d
x
2
;
t
1
;
t
2
g
d
x
1
d
x
2
¼
:
(6.6)
Search WWH ::
Custom Search