Thanks to visit codestin.com
Credit goes to www.scribd.com

0% found this document useful (0 votes)
146 views13 pages

Chapter 02

This document discusses various probability distributions including binomial, hypergeometric, Poisson, and normal distributions. It provides examples of calculating probabilities of events using these distributions with the given parameters. For example, it calculates the probability of obtaining 4 white balls in the 7th draw from a total of 19 balls with 10 white balls using the hypergeometric distribution. It also discusses concepts like lack of memory property of Poisson distribution and transformation of random variables.

Uploaded by

Sudipta Ghosh
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
146 views13 pages

Chapter 02

This document discusses various probability distributions including binomial, hypergeometric, Poisson, and normal distributions. It provides examples of calculating probabilities of events using these distributions with the given parameters. For example, it calculates the probability of obtaining 4 white balls in the 7th draw from a total of 19 balls with 10 white balls using the hypergeometric distribution. It also discusses concepts like lack of memory property of Poisson distribution and transformation of random variables.

Uploaded by

Sudipta Ghosh
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 13

Chapter 2

Distributions


2.1 Let A = { seven appears} = {(1 ,6) , (2 , 5) , (3 , 4) , (4 , 3) , (5 , 2) , (6 , 1)}.
Then, ( ) .
6
5
6
1
1 and
6
1
36
6
) ( = = = = A P A P

(a) This is Bernoulli trials with k = 2 successes and n = 6 trials. Hence,

2009 0
6
5
6
1
! 2 ! 4
! 6
6
5
6
1
2
6
trials) 6 in successes 2 (
4 2 4 2
. n k P = |
.
|

\
|
|
.
|

\
|
= |
.
|

\
|
|
.
|

\
|
|
|
.
|

\
|
= = =

(b) 3349 . 0
6
5
6
5
6
1
0
6
trials) 6 in successes (no
6 6 0
= |
.
|

\
|
= |
.
|

\
|
|
.
|

\
|
|
|
.
|

\
|
= = n P

2.2 The number of ways of obtaining 4 white balls out of 10 is
|
|
.
|

\
|
4
10
. The other
number of different ways of obtaining 3 other balls (not white) is
|
|
.
|

\
|
3
9
. Hence, the
probability of obtaining the fourth white ball in the seventh trial is
3501 . 0
7
19
3
9
4
10
=
|
|
.
|

\
|
|
|
.
|

\
|
|
|
.
|

\
|

or, using the formula of the hypergeometric distribution without replacement, we
have 19 = N balls, 10 = r and 4 = k in 7 = n trials. Hence,


22
Distributions
23
. 3501 . 0
7
19
3
9
4
10
) 4 ( =
|
|
.
|

\
|
|
|
.
|

\
|
|
|
.
|

\
|
= = X P
2.3 The probability of success is 9 . 0 = p while the probability of failure is
1 . 0 1 = = p q .

(a) ) 9 ( ) 8 ( ) 7 ( ) 6 ( zone) in land 6 least (at = + = + = + = = X P X P X P X P P
) 10 ( = + X P

( ) ( ) ( ) ( ) ( ) ( )
( ) ( ) ( ) . . . . .
. . . . . .
998 0 9 0
10
10
1 0 9 0
9
10
1 0 9 0
8
10
1 0 9 0
7
10
1 0 9 0
6
10
10 9
2 8 3 7 4 6
=
|
|
.
|

\
|
+
|
|
.
|

\
|
+
|
|
.
|

\
|
+
|
|
.
|

\
|
+
|
|
.
|

\
|
=

(b) ( ) ( ) ( ) . 1 . 0 1 . 0 9 . 0
0
10
zone) in lands none ( P
10 10 0
=
|
|
.
|

\
|
=
(c) Probability that at least 70
0
/
0
land in zone is
= = = = = = + = ) 10 ( ) 9 ( ) 8 ( ) 7 ( X P X P X P X P
( ) ( ) ( ) ( ) ( ) ( ) ( ) 0.987. 9 . 0
10
10
1 . 0 9 . 0
9
10
1 . 0 9 . 0
8
10
1 . 0 9 . 0
7
10
10 9 2 8 3 7
=
|
|
.
|

\
|
+
|
|
.
|

\
|
+
|
|
.
|

\
|
+
|
|
.
|

\
|

Hence, the program is successful.
2.4 Substitution for 0 = k in the Poisson density function, we have

= = = e X P 2 . 0 ) 0 ( . Hence, = 1.609.

. .
e
.
e .
X P X P X P X P X P
.
219 0
]
! 2
) 609 1 (
609 1 2 . 0 [ 1
)] 2 ( ) 1 ( ) 0 ( [ 1 ) 2 ( 1 ) 2 (
609 1
2
609 . 1
=
+ + =
= + = + = = = >





2.5 Let X represent the Poisson distribution of the incoming calls with
hour 12 = .

Signal Detection and Estimation
24
(a) The probability of more than 15 calls per a given hour is
( )

= = = >
15
0
12
1556 . 0
!
12
1 ) 15 ( 1 ) 15 (
k
k
k
e X P X P
(b) No calls in 15 minute ( 4 / 1 hour) break ) 0 ( = X P in 15 minutes.
Hence,
0498 . 0 ) 0 (
3
= = =

e X P
2.6 X is Poisson distributed and ) 1 ( ) 3 / 2 ( ) 2 ( = = = X P X P . That is,
! 1 3
2
! 2
2


e e . Solving for we obtain
3
4
0
3
4
= = |
.
|

\
|
since 0 = is
not a solution. Therefore,
2636 . 0 ) 0 (
3 / 4
= = =

e X P and
( )
1041 . 0
! 3
3 / 4
) 3 (
3
3 / 4
= = =

e X P
2.7 The lack of memory property is

( )
( )
( )
( )
( )
( )
2
1
2 1
1
1 2 1
1 2 1
2
1
2 1
) | (
x X P e
e
e
x X P
x x X P
x X P
x X x x X P
x X x x X P
x
x
x x
= = =
>
+
=
>
> +
= > +

+

I

2.8 (a) In this case the parameter
12
1 1
=

= and the density function is

=



otherwise , 0
0 ,
12
1
) (
12

x e
x f
x
X

Hence, 2325 0
12
1
1 ) 15 ( 1 ) 15 (
15
0
12
. e X P X P
k
k

= = = >
(b) 0833 . 0
12
1
) 0 ( = = = X P .
Distributions
25
2.9 X is the standard normal X ~ N (0. 1)

(a) )] 1 P( 2[1 ) 1 ( 2 ) 1 ( ) 1 ( ) 1 ( = > = > + < = > X X P X P X P X P
3174 . 0 ) 8413 . 0 2(1 )] 1 ( 2[1 = = = I



(b) 1587 0 ) 1 ( 1 ) 1 ( 1 ) 1 ( . I X P X P = = = >

2.10 X ~ N (0,1). Then, 0013 0 3 3 1 3 1 3 . ) Q( ) I( ) P(X ) P(X = = = = >

2.11 20
0
/
0
of 200 = 40 times. A success is when
X = 7 {(1,6), (2,5), (3,4), (4,3), (5,2), (6,1)}.
Hence, we have success with .
6
5
1 and
6
1
36
6
= = = = p q p

(a) ) 40 ( time) the of 20 least at (success
0
0
= X P P

|
.
|

\
|
|
.
|

\
|
|
|
.
|

\
|
=
200
40
200
6
5
6
1 200
k
k k
k
= 0.1223.
(b) Using the central limit theorem to obtain the approximation to the normal
distribution, we have
. . ) . I(
npq
X-np
-P X P X P 1423 0 07 1 1
36
1000
6
200
39
1 ) 39 ( 1 ) 40 ( = =
|
|
|
|
|
.
|

\
|

=

+1 -1
x
fX(x)
Signal Detection and Estimation
26
2.12
100 2 1
X X X X S
k
+ + + + + = L L , X
k
is Poisson distributed with =3.2
(a)

= =
= = = =
4
1
2 3
100
5
2 . 3
2602 0
!
) 2 3 (
1 ) 4 ( 1
!
) 2 . 3 (
) 5 (
k
k
.
k
k
. .
k
.
e S P
k
e S P
(b) Using the central limit theorem, S becomes normal with mean 3.2 and
variance 3.2. That is S ~ N(0.032 100, 0.032 100) . Hence,
3264 . 0 ) 45 . 0 ( 45 0 1
2 3
2 3 4
2 3
2 3
1 ) 4 ( 1 ) 5 ( = =
|
|
.
|

\
|

= Q ) . I(
.
.
.
. S-
P S P S P
2.13 X ~ N(1, 2)
(a) From the tables,
|
|
.
|

\
|

= >
2
1 2
2
1
1 2 1 2
X
P ) P(X ) P(X
2399 0 707 0 1 . ) . I( = =
(b)
|
|
.
|

\
|

=
2
2 2 2
2
2
2
2 6 1
) 2 2 6 1 (
. X .
P . X . P
. . ) . I( ) . I( .
X
P .
X
P 166 0 28 0 14 0 28 0
2
2
14 0
2
2
= =
|
|
.
|

\
|

|
|
.
|

\
|

=

2.14


=
otherwise , 0
6 1 ,
5
1
) (

x
x f
X










Using the fundamental theorem, we have
2
2
and
1 1
x
dy
dx
dx
x
dy
x
y = = = . Hence,
+ + + + + + x
1 2 3 4 5 6
fX(x)

5
1

Distributions
27
. 1
6
1
for
5
1
5
1
) (
) (
) (
2
2
= = = = y
y
x
dy
dx
x f
dx
dy
x f
y f
X
X
Y












2.15 (a) We found in Example 1.19 for
2
X Y = that

>
=
0 , 0
0 , ) ( ) (
) (
y
y y F y F
y F
X X
Y


and
| |

>
=
0 , 0
0 , ) ( ) (
2
1
) (
y
y y f y f
y y f
X X
Y


For X uniformly distributed between 0 and 1, we obtain

< <

=
1 , 1
1 0 ,
0 , 0
) (
y
y y
y
y F
Y

and

<
=
otherwise , 0
1 0 ,
2
1
) (

y
y y f
Y



1
FY(y)
y
0 1
y
1
fY(y)
1/2


+ + + + + + y

6
1

6
2

6
3

6
4

6
5
1
5
1

fY(y)
5
36

Signal Detection and Estimation
28
(b) For e Z
X
, =
) ( ) ( z Z P z F
Z
=

> = =

=
0 , ) (ln ) ln ( ) (
0 , 0
z z F z X P z e P
z
X
X

Hence,

>
=
0 , 0
0 , ln
z
z z) ( F
(z) F
X
Z
. The density function is

>
= =
0 , 0
0 , ) (ln
1
) (
) (
z
z z f
z
dz
z dF
z f
X Z
Z


Substituting for z, we obtain

<
<
=
e z
e z z
z
z F
Z
, 1
1 , ln
1 , 0
) ( and


=
otherwise , 0
1 ,
1
) (

e z
z z f
Z


2.16 X and Y are standard normal, that is
2
2
2
1
) (
x
X
e x f

= and
2
2
2
1
) (
y
Y
e y f

= .
(a)

<
>
= =
0 ,
0
Y
Y
X
Y ,
Y
X
Y
X
Z


The distribution function of Z is
|
|
.
|

\
|
< +
|
|
.
|

\
|
> = = 0 0 ) ( ) ( Y z
Y
X
P Y z
Y
X
P z Z P z F
Z

) y yz X P( ) y yz X P( 0 0 < + > = with the regions shown
below.
Distributions
29

( ) ( )




+


=
=
+ =
0
2 2
0
2 2
0
0
0
0
2 2 2 2
2
1
2
1
) , (
) , ( ) , ( ) (
dy e ye

dy e ye


yz,y)dy ( yf dy y yz yf
dxdy y x f dxdy y x f z F
y yz y yz
-
XY XY
yz
XY
y
XY Z


Using Leibnizs rule, we obtain
z.
z
z f
Z
all for
) 1 (
1
) (
2
+
=
(b) For
Y
X
W = , we have .
Y
X
Y
X
Z
Y
X
Z = = = Thus,

<
>
= = =
0
0
Z , Z
, Z Z
Z
Y
X
W .











Using the fundamental theorem of transformation of random variables, we have

x < -yz
y < 0
y
x
x=-yz
y
x
x=yz
x<yz
y>0
w
w
z
z
1
z
2
Signal Detection and Estimation
30

) ( '
) (
) ( '
) (
) (
2
2
1
1
z g
z f
z g
z f
w f
Z Z
W
+ = where w z =
1
and w z =
2
.
Also, 1 ) (
0 1
0 1
) ( ' =

<
> +
= z g'
z ,
z ,
z g .

Substituting, we obtain

( ) ] 1 [
1
] 1 [
1
) ( ) ( ) (
2 2
2 1
+
+
+
= + =
w w
z f z f w f
Z Z W

Therefore, . w
w
w f
W
<
+
= 0 for
) 1 (
2
) (
2


2.17 The joint density function of ) , (
2 1
X X is
( )
2
2
2 1
2 1
2
2
2 1
2
1
) , (

+

=
x x
X X
e x x f with
2
1
2
2
2
2
1 1
and
X
X
Y X X Y = + = .
Solving
2 2 1
2
1
2
2
2
1
and y x x y x x = = + , we obtain
( )
2
2
2 1
1
2
2
1
2
2
1
2
2
2
2
2
1
2
2
2
2
2
2
1
and
1
1
y
y y
x
y
y
x y y x y x y x
+
=
+
= = + = +
By definition, 0
1
y since
2 2 1
y x x = and hence, we have 2 solutions:
2
2
1
2
2
2
1 2
1
2
2
1
2
2
2
1 2
1
1 1
1 1
y
y
x
y
y y
x
y
y
x
y
y y
x
+
=
+
=
+
=
+
=



The Jacobian of the transformation is
Distributions
31
( ) ( )
1
2
2
1 1
2
2
2 / 1
2
2
2
1
2 / 1
2
2
2
1
2
2
2
1
2
2
1
2
2
2
2
1
2
2
2
2
1
1
2 1
1 1 1
1 1
1
) , (
y
y
y y
y
x x x x
x
x

x
x

x

x x
x

x x
x
x x J
+
= =
+

+
=

+ +
=

Therefore,
(
(
(

|
|
|
.
|

\
|
+

+
|
|
|
.
|

\
|
+ +
+
=
2
2
1
2
2
2 1
2
2
1
2
2
2 1
2
2
1
2 1
1
,
1 1
,
1
1
) , (
2 1
y
y
y
y y
f
y
y
y
y y
f
y
y
y y f
XY XY Y Y

Note that ) , ( ) , (
2 1 2 1
2 1 2 1
x x f x x f
X X X X
= . Hence,
) ( ) ( ) (
2
1
1
2
) , (
2 1 1
2
2 2
2
1
2 1
2 1
2 2
1
2 1
y f y f y u e
y
y
y y f
Y Y
y
Y Y
=
+
=


where, ) ( ) (
1
2
1 1
2 2
1
1
y u e ky y f
y
Y

= . We determine the constant k to be

= =
0
2
1
2
1
1
1
2 2
1
k dy e y k
y
. Thus, the density function of Y
1
and Y
2
are
respectively
) (
2
1
) (
1
2
2
1
1
2 2
1
1
y u e
y
y f
y
Y

=
and
2
2
2
1
1 1
) (
2
y
y f
Y
+

=


Signal Detection and Estimation
32
2.18 X is a standard normal
2
2
2
1
) (
x
X
e x f

= .
Y is a chi-square distributed random variable with n degrees of freedom
( )
0 for
2 / 2
1
) (
2
1
2
2 /
> =

y e y
n
y f
y n
n
Y

Let
n Y
X
T
/
= , then the cumulative distribution of T is
( )
( )

= = =
0
/
2
) (
1
2
2 /
2
2 2 / 2
1
/ ) ( ) (
n y t x y n
n
T
dxdy e y
n
n y t X P t T P t F
since the region of integration is the xy-plane with n y t x / . Note that the joint
density function of X and Y is just the product of the individual density functions
since we assume X and Y independent. Making the change of variables
n y u x / = , then du n y dx / = and ) / (
2 2
n y u x = . Substituting in the
integral, we obtain
( )
( )


=

=
|
|
.
|

\
|
+



(
(
(

=
t
u y
n
u y
n
n
t
n
y u y n
n
T
du dy e y
n
dudy e
n
y
e y
n
t F
0
1
2
2
1
2 /
0
2
1
2
2 /
2
2
2 2 / 2
1
2 2 / 2
1
) (


Let dz
n
u
dy z
n
u
y z
n
u y
2 2
2
1
2
and
1
2
1
2
+
=
+
= =
|
|
.
|

\
|
+ . The integral
becomes
Distributions
33
( )

=

=
+

+
(
(
(
(
(
(
(

|
|
.
|

\
|
+

=
t
u z
n
z
n
n
n
T
du dz
n
u
e z
n
t F
0
2
1
2
2
1
2 /
2
1
1
2 2 / 2
2
) (

( )
du
n
u
n n
n
t
u
n

=
+
|
|
.
|

\
|
+

|
.
|

\
| +
=
2
1
2
1
1
2 /
2
1


since .
n
m
n
m m dz e z
z m
2
1
with
2
1
) 1 ( !
0

= |
.
|

\
| +
= + = =



Taking the derivative of F
T
(t) using Leibnizs rule, we obtain the required density
function given by (2.171).

2.19 With = 0, the Cauchy density function is given by .
1
) (
2 2
x
x f
X
+

=
The moment generating function of X is then


+
+

=
+

= = dx
x
x
j dx
x
x
dx
x
e
e E
x j
X j
x
2 2 2 2 2 2
sin cos
] [ ) (
since x j x e
x j
+ =

sin cos . Also, 0 ) ( lim =


p
p
p
dx x f when f(x) is an odd
function of x. Then,

=
0
2 2
cos 2
) ( dx
x
x
x

since
2 2
cos
x
x
+

is even. Using the tables of integrals, we obtain
. 0 and 0 ) ( > > =

, e
x

Signal Detection and Estimation
34
2.20 (a) The mean value of Weibull distribution is given by
. ] [
0
dx e abx X E
b
ax b

=

Let
b
b b b
a
u
bu
du
dx
x
dx
ax b dx abx du ax u
/ 1
1
) ( |
.
|

\
|
= = = =

since
b
a
u
x
/ 1
|
.
|

\
|
= .
Hence, |
.
|

\
|
+ = = |
.
|

\
|
=


b
a du e u a du
a
u
bu
ue b X E
b u b b
b
u
1
1
1
] [
/ 1
0
/ 1 / 1
0
/ 1
.

(b) The variance is ( )
2 2 2
] [ ] [ X E X E = . We need to determine the mean
square value, which is . ] [
0
1 2
dx e abx X E
b
ax b

+
= Following the same approach as
in (a), we obtain

|
.
|

\
|
+ = =

b
a du e u a X E
b
u
b b
2
1 ] [
2
0
2 2
2
. Hence,

|
.
|

\
|
+ |
.
|

\
|
+ =

2 2
2
1
1
2
1
b b
a
b

You might also like