You are on page 1of 9

# PTSP‐UNIT V    Questions & Answers

GRIET‐ECE    1
UNIT – 5
1. Find the expected value and dispersion of the discrete random variable X
whose probability distribution is given below:
X 1 2 3 4 5
P(X= x) 0.1 0.1 0.3 0.3 0.2

Ans: m = E[X]
= ∑ x
ì
P(X = x
ì
)
5
ì=1

= 1*(0.1) + 2*(0.1) + 3* (0.3) + 4 *(0.3) +5*(0.2)
= 0.1 +0.2 +0.9 +1.2 +1.0
= 3.4
The expected value of X =3.4
o
X
2
= (x
ì
- m)
2
P(X = x
ì
)
5
ì=1

= [(1-3.4)
2
*0.1] + [(2-3.4)
2
*0.1] + [(3-3.4)
2
*0.3] + [(4-3.4)
2
* 0.3] + [(5-3.4)
2
*0.2]
= 1.44
The dispersion of X = 1.44
2. Find the coefficient of variation between X and Y from the following data:
X 1 2 3 4 5 6 7 8 9
Y 9 8 10 12 11 13 14 16 15

Ans: Coefficient of correlation is
ρ
X Y
=
con¡(X,¥)
c
X
c
Y

conv(X, Y) = E (XY)-E(X).E(Y)
E(X) =
1+2+3+4+5+6+7+8+9
9
=5
www.jntuworld.com
www.jntuworld.com
GRIET‐ECE    2
E(Y) =
9+8+10+12+11+13+14+16+15
9
=12
E (XY) =
1-9+2-8+3-10+4-12+5-11+6-13+7-14+8-16+9-15
9
= 12
Var(X) =E(X
2
)-[E(X)]
2

E(X
2
) =
1+4+9+16+25+36+49+64+81
9
=31.66
Var(X) =31.66 – 25 = 6.66
Ö o
X
= 2.58

Var(Y) =E(Y
2
) – [E(Y)]
2

E(Y
2
) =
81+64+100+144+121+169+196+256+255
9
= 150.66
Var(Y) = 150.66 -144 =6.66
Ö o
¥
= 2.58
Conv(X,Y) = E(XY) –E(X).E(Y)
= 66.3 – (5) *12 =6.3
p

=
6.3
(2.58)(2.58)
= 9.46

3. If X and Y are independent random variables, show that
E[XY] =E[X].E[Y]
And E[g
1
(X).g
2
(X)] =E[g
1
(X)] E[g
2
(X)] ?
Ans:
E(XY) = ] ] xy ¡(x, y)JxJy
«

«

= ] ] xy ¡(x)¡(y)JxJy
«

«

= ] x ¡(x)
«

Jx ] y ¡(y)
«

Jy
= E[X].E[Y]
www.jntuworld.com
www.jntuworld.com
GRIET‐ECE    3
Consider E[g
1
(X).g
2
(X)] =] ] g
1
(x)g
2
(y)¡(x, y)JxJy
«

«

= ] ] g
1
(x)g
2
(y)¡(x)¡(y)JxJy
«

«

= ] g
1
(x)¡(x)
«

Jx ] g
2
(y) ¡(y)
«

Jy
= E[g
1
(X)] E[g
2
(X)]
4. Let X and Y be the independent random variable s each having density
function
f(x) =2 e
-2a
for u ≥ 0
= 0 elsewhere
Find (a) E(X+Y)
(b) E(X
2
+Y
2
)
(c) E (XY)
Ans:
(a) E(X+Y) = ] ] (x + y) ¡(x, y)JxJy
«
0
«
0

Since it is given that X and Y are identically distributed independent random variables,
f(x y) =f(x).f(y)
E(X+Y) = ] ]
(x + y)2c
-2x
2c
-2¡
JxJy
«
0
«
0

= |] 2x
«
0
c
-2x
Jx ] 2
«
0
c
-2¡
Jy +] 2y
«
0
c
-2¡
Jy ] 2
«
0
c
-2x
Jx ]
We have ] 2
«
0
c
-2x
Jx = ] 2
«
0
c
-2¡
Jy = 1
Therefore E(X+Y) = ] 2x
«
0
c
-2x
Jx +] 2y
«
0
c
-2¡
Jy =1
(b) E(X
2
+Y
2
) = ] ]
(x
2
+ y
2
)2c
-2x
2c
-2¡
JxJy
«
0
«
0

= j] 2x
2
«
0
c
-2x
Jx ] 2
«
0
c
-2¡
Jy +] 2y
«
0
2
c
-2¡
Jy ] 2
«
0
c
-2x
Jx [
= ] 2x
2
«
0
c
-2x
Jx +] 2y
«
0
2
c
-2¡
Jy =1
www.jntuworld.com
www.jntuworld.com
GRIET‐ECE    4
(C) E(XY) = ] ]
(X¥)2c
-2x
2c
-2¡
JxJy
«
0
«
0

= ] 2x
«
0
c
-2x
Jx + ] 2y
«
0
c
-2¡
Jy
= (1/2)(1/2) =1/4

5. Let X and Y be the random variables having joint density function
f(X,Y) =X+Y for 0 X 1, 0 Y 1
= 0 otherwise.
Find (a) var(X)
(b) Var(Y) (c) o
XY
(d) ρ
Ans: f(x) =] ¡(x, y)
1
0
=] (x + y)Jy
1
0

jxy +
¡
2
2

0
1
= x+1/2
E(X) = ] x ¡(x)Jx
1
0
=] x |x +1¡2] Jx
1
0

j
x
3
3
+
x
2
4

0
1
=7/12
E(X
2
) = ] x
2
¡(x)Jx
1
0
= ] x
2
|x +1¡2]Jx
1
0

j
x
4
4
+
x
3
6

0
1
= 5/12
Var(X) = E(X
2
) – [E(X)]
2

= 5/12 – 49/144
= 11/144
(b) f(y) = ] ¡(x, y)
1
0
=] (x +y)Jy
1
0
f
jxy +
x
2
2

0
1
= y+1/2
E(Y) = ] y ¡(y)Jy
1
0
=j
¡
3
3
+
¡
2
4

0
1
=7/12
www.jntuworld.com
www.jntuworld.com
GRIET‐ECE    5
E(Y
2
) = ] y
2
¡(y)Jy
1
0
= j
¡
4
4
+
¡
3
6

0
1
= 5/12
Var(Y) = 11/144
(c) Conv(X,Y) =o

= E (XY) –E(X) E(Y)
E(XY) = ] ] xy
1
0
1
0
¡(x, y)JxJy
= ] ] xy
1
0
1
0
(x +y)JxJy
= ] ] (x
2
y +xy
2
)
1
0
1
0
JxJy
= ]
x
3
¡
3
+
x
2
¡
2
2
¡
0
1
1
0
Jy
= ] j
¡
3
+
¡
2
2
[
1
0
Jy
= j
¡
2
6
+
¡
3
6
[ = 1/3
Conv(X,Y) =1/3 –(7/12)*(7/12) = -1/144
(d) ρ =
co¡ (X,¥)
c
X
c
Y

Since o
X
= o
¥
=
√11
12

Therefore
ρ =
-1¡144
11¡144
=-1/11
6. If x ,Y and Z are random variables with same variance ,find the correlation
coefficient between (X+Y) and (Y+Z). Let X and Y and Z are of zero mean
and are independent?
Ans:
Given data:
p

= p

= p

= u
E(X+Y) =E(X) = E(Y) =0
www.jntuworld.com
www.jntuworld.com
GRIET‐ECE    6
Var(X+Y) = E[|X + ¥ -E(X + ¥)|
2
]
= E[(X+Y)
2
]
= E[X
2
+Y
2
+2XY]
= E[X
2
] + E[Y
2
] +2.E[X.Y]
= E(XY) = E(X) .E(Y) = 0
Since mean is zero, mean of X ,Y and Z are same as mean square values and as given by ,they
are equal.
Var(X+Y) = E[X
2
] + E[Y
2
]
= 2 E[Y
2
]
Ö ¸2 vai(Y) = o
X+¥

Similarly var(Y+Z) = E[Z
2
] + E[Y
2
]
=2 E[Y
2
]
u
Ö ¸2 vai(Y) = o
¥+z

Conv[(X+Y),(Y+Z)] = E[(X+Y)(Y+Z)] – E[X+Y]. E[Y+Z]
= E[XY + XZ + Y
2
+ YZ]
= E(XY) + E(XZ) + E(Y
2
) + E(YZ)

= E(Y
2
) = var(Y)
p
(X+¥)(¥+z)
=
Conv|(X+Y),(Y+Z)]
c
X+Y
c
Y+Z

=
¡u¡(¥)
2.¡u¡(¥)
=1/2
7.Explain when random variables are called jointly random Gaussian, and
also list important properties of Gaussian random variable?
Ans: The two random variables X and Y are said to be joint Gaussian if their joint density
function is of the form
www.jntuworld.com
www.jntuworld.com
GRIET‐ECE    7
¡
x,¡
(x, y) =
1
2Пo
X
o
¥
¸1 - p
2
cxp
= _
-1
2(1-p
2
)
_
(x-X)

2
c
X
2
-
(x-X)

(¡-¥

)
c
X
c
Y
+
(¡-¥

)
c
Y
2
__
Which is sometimes called the bivariate Gaussian density
Here X

= E|X] ¥

= E|¥],
o
X
2
= E[(X - X

)
2
] o
¥
2
= E[(¥ - ¥

)
2
]
ρ = E
|(X-X
)(¥-¥

)]
c
X
c
Y

Properties of Gaussian random variables:
1. Gaussian random variables are completely defined through only their first and second order
moments ,i.e., by their means ,variance and co variances
2. If the random variables are un correlated, they are also statically independent.
3.Random variables produced by a linear transformation of X
1
……………………X
N
will also
be Gaussian.
4. The conditional density
¡
X
1
………………………X
N
= j
x
1
……………………….x
k
¥
K+1
=X
K+1
……………….X
N
=x
N
[is Gaussian, K< N
.
8. The joint pdf of two random variables X and Y is given as
¡
XY
= c(2x +y) for 0 ≤ x ≤ 2
= 0 for 0 ≤ y ≤ 3 elsewhere
Determine the values of constant C ?
Ans:
For a joint PDF we know that
] ] ¡

(x, y)
«

«

JxJy = 1
Putting the values of ¡

(x, y), we get
www.jntuworld.com
www.jntuworld.com
GRIET‐ECE    8
] ] c(2x + y)

-∞

-∞
JxJy = 1
c ] j
2x
2
2
+yx[ Jy = 1
3
0

c ]
|2y +4]Jy = 1
3
0

c j

2
2
+4y[¡
0
3
=1

c|y
2
+ 4y]|
0
3
=1

21c = 1

C=1/21

9. Two random variables X and Y has the following joint probability
distribution function as
f (x y ) = 2-x-y, for 0 ≤ x ≤ 1
= 0 elsewhere
Find the var(X) and var(Y)
Sol:
We have
f (x) =] ¡(x, y)
1
0
Jy =j
3
2
-x[

f (y) = ] ¡(x, y)
1
0
Jx =j
3
2
- y[

E[X] = ] x. ¡(x). Jx
1
0
=] x. |
3
2
-x]. Jx
1
0
=_
3x
2
4
+
x
3
3
¡
0
1
_ = 5/12

E[X
2
] = ] x
2
. ¡(x). Jx
1
0
= ] x
2
|
3
2
- x ]. Jx
1
0
=
x
3
2
-
x
4
4
¡
0
1
=1/4
Var(X) =E[X
2
] –[E[X]]
2

=1/4 - 25/144

= 11/144

www.jntuworld.com
www.jntuworld.com
GRIET‐ECE    9
Similarly Var(Y) =11/144

10. If x is a random variable for which E(X) =10 and var(X) =25 , for
what possible value of ‘a’ and ‘b’ does Y=aX-b have exception 0 and
variance 1 ?
Ans:
E[aX-b] = aE[X]-b = 0

10a-b = 0
E[(Y-Y

)
2
] = E[(aX-b-Y

)
2
] =1

Where Y

is mean of Y and is equal to 0

Therefore E[(aX-b)
2
] = 1

E[a
2
X
2
+b
2
-2aXb] =1

a
2
E[X
2
] +b
2
– 2abE[X] =1

a
2
E[X
2
] +b
2
=1

since var(X) = 25

= E(X
2
) – [E(X)]
2

But E(X
2
) =25 +100 =125

125a
2
+ b
2
= 1

10a – b = 0

10a =b

Therefore 125a
2
-100a
2
= 1

a
2
=1/25

a=1/5
b=2
www.jntuworld.com
www.jntuworld.com