www.LearnEngineering.

in

UNIT – I
RANDOM VARIABLES
1. What do you meant by probability?
Answer: The word "probability" that denotes that there is an uncertainty about the happening of
event. It can also be defined as an expression of likelihood or chance of occurrence of an event. The
probability is a number, which ranges from 0 to 1.

2. Define Event.
Answer: An outcome or a combination of outcomes of a random experiment is called an event.
Events are generally denoted by capital letters A, B, C, etc. For Example: If a coin is tossed, getting a

n
head or tail is an event.

g.i
3. Define the term random experiment.
Answer: The term experiment is used to describe an act, which can be repeated under some

rin
conditions. Random experiment is one which result depends on chance. That is the results can never
be predicted. For example: Tossing a coin, throwing a die.

4. Define Mutually Exclusive events.

ee
Answer: Two events if the occurrence completely excludes the occurrence of the other. That is the
gin
two events cannot occur simultaneously. For Example: Tossing a coin, either head or tail will turn
up.
En

5. Define Equally likely events.

Answer: Events are said to be equally likely when one does not occur more often than others. For
Example: If an unbiased coin or die is thrown, each face may be expected to be observed
arn

approximately the same number of times in the long run.

6. Define compound Events.

Le

Answer: The joint occurrence of two or more events is called compound events.

7. Define sample space.

w.

Answer: The set of all possible outcomes of a given experiment is called its sample space. Each
element of the sample space is called a sample point.
For example: When a die is thrown, the sample space S= 1, 2, 3, 4, 5, 6
ww

8. Define Independent Events?

Answer: Two events are said to be independent if the occurrence of one does not affect the
occurrence or non-occurrence of the other.

9. State the three axioms of probability?

Answer: 1. The probability of any event ranges from zero to one. i.e 0 ≤ P (A) ≤ 1
2. The probability of the entire space is 1, that is P (S) = 1
3. If A and B are mutually exclusive events, then the probability of occurrence of
either A or B denoted by P (A∪B) i.e P (A∪B) = P (A)+ P (B)
2

www.LearnEngineering.in
www.LearnEngineering.in

10. Define non-independent events?

Answer: If the occurrence of one event is affected by the occurrence of the other event, then the two
events are said to be non-independent Events.

11. What do you meant by exhaustive events?

Answer: Events are said to be exhaustive when their totality includes all the possible outcomes of a
random experiment.

12. What do you meant by conditional probability?

Answer: Two events A and B are said to be dependent when B can occur only when A is known to
have occurred. The probability attached to such an event is called conditional

n
P(A/B) =P (A∩B)/P(B)

g.i
13. Write short notes on Baye's Theorem.
Answer: Let B1, B2, ..., Bn be a exhaustive and mutually exclusive random experiments and A an

rin
P( Bi ) P( A / Bi )
event related to that Bi, then P( Bi / A)  n
 P( Bi ) P( A / Bi )
i 1
ee
14. Define Random variable.
gin
Answer: A real valued function defined on the outcome of a probability experiment is called a
random variable.
En

15. Define discrete random variable with an example.

Answer: A random variable whose set of possible values is either finite or countably infinite is called
the discrete random variable.
arn

Example : Number of transmitted bits received in error.

16. What is the Probability mass function?

Answer: For a DRV ‘X’ with possible values x1 , x2 , x3 , … . xn , a probability mass function is a
Le

function such that a) P(X = xi ) ≥ 0 b) ∑ni=1 P(X = xi ) = 1.

w.

17. Define Cumulative distribution function of a DRV.

Answer: The cumulative distribution function of a discrete random variable is denoted as F(x) such
that F(x) = P(X < x).
ww

18. What do you mean by the Mean of a DRV?

Answer: The mean or an expected value of a discrete random variable is denoted as
μ = E(x) = ∑x x P(x).

19. Define expected value of a CRV.

Answer: The mean or an expected value of a continuous random variable is denoted as
∞
μ = E(x) = ∫−∞ xf(x)dx.

www.LearnEngineering.in
www.LearnEngineering.in

20. If a random variable X takes the value 1, 2, 3, 4 such that

2P(X = 1) = 3P(X = 2) = P(X = 3) = 5P(X = 4). Find the probability distribution.

k k k
Answer: Let P(X = 3) = k, then P(X = 1) = 2 , P(X = 2) = 3 , P(X = 4) = 5
We know that, the total probability = 1
i.e., P(X = 1) + P(X = 2) + P(X = 3) + P(X = 4) = 1
k k k 61k 30
+ + k+ =1 ⇒ =1 ⇒ k = 61.
2 3 5 30
The probability distribution is given by,
X=x : 1 2 3 4
P(X = x): 15/61 10/61 30/61 6/61.

n
21. Write the relationship between Cumulative distribution function F(x) and the probability

g.i
density function f(x) .
d
Answer: f(x) = F(x).
dx

rin
22. Define Moment generating function.

Answer: MX (t) = E(e tx )

= { ∞ tx
ee
∑x etx P(x) , if X is a discrete random variable
∫−∞ e f(x)dx , if X is a continuous random variable.
gin

23. If X is a poisson variate such that P(X = 2) = 9P(X = 4) +90 P(X = 6), find the variance.
e−λλx
Answer: We know that, P(X = x) = , x = 0,1,2….. and λ > 0.
En

x!
e−λλ2 e−λ λ4 e−λ λ6 32 4 1
2!
=9
4!
+ 90
6!
⟹  
8 8 2
arn

⟹ 4  32  4  0 ⟹ ( 2 + 4) ( 2 - 1) = 0 ⟹  = variance = 1.

24. A CRV ‘X’ has pdf given by 𝐟(𝐱) = 𝟑𝐱 𝟐 , 0≤ 𝐱 ≤ 𝟏.Find K such that 𝐏(𝐱 > 𝐾 ) = 𝟎. 𝟎𝟓.
Le

Answer:
1
Given, P(x > 𝐾 ) = 0.05. ⟹  f ( x)dx  0.05
w.

k
1

 3x dx  0.05 ⟹ 1 − k 3 = 0.05
2
⟹
ww

⟹ k = (0.95)1/3 = 0.9830.

25. Write the MGF of Binomial distribution.

Answer: MX (t) = (q + pet )n .

26. The mean of the binomial distribution is 20 and standard deviation is 4. Find the parameters
of the distribution.
Answer: Given, mean = np = 20 & variance = npq = 16.

www.LearnEngineering.in
www.LearnEngineering.in

npq 16 4 1
  q  p  1 q 
np 20 5 5
20
And n =  20(5)  100.
p

27. X is a discrete R.V having the p.m.f X: -1 0 1

P(X): k 2k 3k. Find P( X ≥ 0).
Answer: WKT,  P( x i )  1  6k = 1  k= 1/6.
P(X ≥ 0) = P(0) + P(1) = 2/6 + 3/6 = 5/6.

n
28. The random variable X has the p.m.f. P(x) = x/15, x = 1, 2, 3, 4, 5 and = 0 elsewhere.
Find P( 1/2 < X < 5/2 / X > 1 ).

g.i
P( A  B)
Answer: WKT, P( A / B) =
P( B)

rin
P[(1 / 2 < X < 5/2)  (X  1)] P( X  2) 2 / 15
Now P( 1/2 < X < 5/2 / X > 1) = = =  2 / 14.
P(X  1) 1  P( X  1) 1  (1 / 15)
ee
29. If the p.d.f of a R.V.X is f(x) = x / 2 in 0 ≤ x ≤ 2, find P( X > 1.5 / X > 1).
Answer:
gin
P[ ( X  1.5)  ( X  1)] P( X  1.5)
P(X > 1.5 / X > 1) = = ..................(1)
P( X  1) P( X  1)
2
2 2
 x2  (1.5) 2
En

P(X > 1.5) =  f ( x)dx   ( x / 2)dx    1  1  0.5625  0.4375 ................(2)

1.5 1.5  4  1.5 4
2
2
 x2 
P(X > 1) =  ( x / 2)dx    1 1 / 4  0.75 ...................(3)
arn

1  4 1
Using (2) & (3) , (1) becomes
P(X > 1.5 / X > 1) = 0.4375/0.75 = 0.5833.
Le

1
30. A random variable X has the probability function P(x = ), x = 1,2,3.... find its m.g.f.
2x
w.

x

1  
 et 
Answer: MX (t) =  e P( x)   e x 
tx tx
1  2 
x 1 1 2  
ww

 et  et  2  et 3 
=         .........
 2  2   2  

et  et  et  
2

= 1      ...........
2 2 2 

1
et  et  et  2  et
= 1     t 
 .
2e  2e
t
2  2 2

www.LearnEngineering.in
www.LearnEngineering.in

31. If the density function of a continuous r.v X is given by

ax , 0 ≤ x ≤ 1
f(x) = a , 1≤x≤2 find a.
3a – ax , 2 ≤ x ≤ 3
0 , otherwise

 3
Answer: WKT,  f ( x)dx  1

  f ( x)dx  1
0
1 3
1 2 3
 ax 2   ax 2 
 ax dx   a dx   (3a  ax)dx  1     ax 2
1  3ax    1.

n
0 1 2  2 0  2 2

g.i
(a/2) + a + [ (9a – 9a/2) – (6a – 2a) = 1  a 1 / 2.

rin
32. If f(x) = K e –x, x > 0
0 , otherwise is the p.d.f of a random variable X, then find K.
Answer: ee
  

   Ke
x
WKT, f ( x)dx  1  f ( x)dx  1  dx  1
gin
 0 0

 e x 
 K    1
 1 0
En

 K = 1.
(2e t  1) 4
33. Let X be a r.v with m.g.f M X (t) = , then find its mean and variance.
81
arn

Answer: WKT, MX(t) = ( q + pet)n ..............(1)

Given, MX(t) = ( 1/3 + 2/3et)4 .............(2)
From (1) & (2) , we get n = 4 , p = 1/3 , q = 2/3
Le

Wkt, mean = np = 4/3 & variance = npq = 8/9.

34. Show that the function f(x) = e –x, x > 0 is a p.d.f of a r .v X.

w.

0, otherwise

Answer: We have to prove  f ( x)dx 1
ww



  
 e x 
Now  f ( x)dx   e dx   x
  (1) (0 1)  1
0 0  1 0
Hence the given function is a probability density function of a r.v X.

35. The mean and variance of binomial distribution are 5 and 4. Find the distribution.

Answer: Given , mean = np = 5 & variance = npq = 4

www.LearnEngineering.in
www.LearnEngineering.in

npq 4 4 1
   q  p  1 q 
np 5 5 5
5
Now np = 5  n= = 25
p
x 25 x
1  4
Hence the distribution is P( X=x ) = nCx p q x n-x
= 25Cx    
5  5

𝟑/𝟒(𝟐𝒙 − 𝒙𝟐 ), 𝟎<𝑥<2
36. Assume that X is a CRV with p.d.f f(x) = { 𝟎, 𝒐𝒕𝒉𝒆𝒓𝒘𝒊𝒔𝒆 Find P(X > 1).

n
2
3  x2 x3 
 
2
3
  

g.i
Answer: P ( X > 1 ) = 2 x  x dx =
2
2
1
4 4  2 3 1
3  8  1   3   2  1
 4    1   =     = .

rin
= 
4   3  3   4   3  2

ee
37. A r.v X is uniformly distributed between 3 and 15. Find the variance of X.
gin
1 1
Answer: Wkt , f( x) = , a<x<b  f(x) = , 3  x  15
ba 12
b  a 2 
12 2
 12.
En

Wkt , Variance =
12 12

38. Find the m.g.f of Poisson distribution.

arn

e  x
Answer: Wkt, P( X = x ) =
x!
 
e  x
Le

Now MX (t) = E ( e tx ) =  e tx P( x) =
x 0
 e tx
x 0 x!
  e t e   t 2    e t
 e  e 1 .
w.

t
= e   1    ........... = e e
 1! 2! 
0 , x<0
ww

𝟏
39. The c.d.f of the r.v X is given by FX (x) = x + 𝟐 , 0 ≤ x ≤1/2 Find P ( X > ¼ ).
1 , x >1/2

d
Answer: Wkt, f(x) = F (x)
dx
0, x<0
 f(x) = 1 , 0≤ 𝑥 ≤ 1/2
0 , x > 1/2

www.LearnEngineering.in
www.LearnEngineering.in

1/ 2 1/ 2 1/ 2

 dx  x
1 1 1
Now P ( X > 1/4 ) =  f ( x)dx
1/ 4

1/ 4
 
2 4
 .
4
1/ 4

40. Find the variance of the DRV X with the p.m.f PX (x) = 1/ 3 , x = 0
1/ 2 , x = 2

Answer: Var (X) = E(X2) - [ E(X) ]2 ...................(1)

Now E(X) = x i p ( xi ) = 0.p(0) + 2. p(2) = 0 + 2 (1/2) = 1.

n
x
2
E(X2) = p ( xi )  0 2. p (0)  2 2 p (2) = 4(1/2) = 2.

g.i
i

Now (1) becomes, Var (X) = 2 – 1 = 1.

rin
41. X and Y are independent r.v’s with variance 2 and 3. Find the variance of 3X + 4Y.
Answer: Given, Var (X) = 2 & Var (Y) = 3
Var( 3X + 4Y) = 32 Var(X) + 42 Var(Y) ee
= 9(2) + 16 (3) = 66.
gin
3x2 , 0 ≤ x ≤ 1
42. A CRV X has ths p.d.f f (x) = Find k such that P(X > k) = 0.5.
0 , otherwise
En

Answer: Given, P(X > k) = 0.5

1
1
 3x 3 
 3x dx  0.5     0.5  1  k 3  0.5
2
ie,
 3 k
arn

 k 3 = 0.5  k = 0.51 / 3  0.7937

c
Le

43. Find c , if a CRV X has the density function f(x) = ,    x  .

1 x2
 

2c tan 1 ( x)0 = 1
c
 1 x

f ( x)dx  1  dx  1 
w.

Answer: Wkt, 2
 

  1
 2c   0 = 1  c = .
ww

2  

44. A r.v X has c.d.f FX(x) = 0 , x< 1

½(x-1) , 1 ≤ x < 3 Find the p.d.f of X and the expected value of X.

1 , x ≥ 3.
d
Answer: The p,d,f of X is given by f(x) = F (x) = 0 , x < 1
dx
½ , 1 ≤ x <3
0, x≥3
8

www.LearnEngineering.in
www.LearnEngineering.in

3
3 3
x2  9 1
Expected value of X = E(X) = 1 xf ( x)dx  1 ( x / 2)dx   4   4  4  2.
1

45. Find the m.g.f of binomial distribution. [ A.U.M/J 2013, N/D 2017]
Answer: For binomial distribution P(X = x) = nCx px qn-x
n
M.G.F = MX (t) = E ( e tx ) = e
x 0
tx
P( x)

 
x

 nCx pe t q n x = q  pe t 
n n

 e tx nCx px qn-x
n
= =
x 0 x 0

n
g.i
46. Define geometric distribution.

rin
Answer: A r.v X is said to follow geometric distribution if it assumes non-negative values and its
probability mass function is given by
ee qx-1 p , x = 1,2,3...
P(X= x) = qx p , x = 0,1,2... Where q = 1 – p and 0 ≤ 𝑝 ≤ 1.
gin
𝒕
47. The m.g.f of a r.v X is given by M(t) = 𝒆𝟑(𝒆 −𝟏) . What is P[ X = 0] ?
e  e 1
t
  3
𝑡 −1)
Answer: Given , M(t) = 𝑒 3(𝑒 =
En

e  x
Wkt, P( X = x ) =
x!
arn

e 3 30
Now P(X = 0) =  e 3 .
0!
48. Establish the memory less property of the exponential distribution.
Le

Answer: If X is exponentially distributed with parameter  , then for any two positive integers m & n
such that
P [ X > m+n / X > m ] = P [ X > n].
w.

P( A  B)
 x
Proof : WKT, P( A / B) = P( B) , and the P.d.f of X is f(x) =  e , x ≥ 0
ww

P[ X  m  n  X  m] P[ X  m  n]
Now P [ X > m+n / X > m ] = P[ X  m] = P[ X  m] .......(1)
  
 e  x 
 f ( x)dx   e
 x
dx     e 
 x

 e  m
   m
m
P[ X > m] = m m

Now (1) becomes ,

e   m n 
 m
 e n  P[ X  n].
P [ X > m+n / X > m ] = e

www.LearnEngineering.in
www.LearnEngineering.in

2
x
b
49. A r.v X is known to have a distribution function F(x) = u(x) [ 1 - e ] ,where b > 0 is a
constant.. Determine its density function. [ A.U N/D 2016]
d d 2
F (x) x
b
Answer: Wkt, by f(x) = dx = dx { u(x) [ 1 - e ]}
2 2
x x
b b
= u’(x) [ 1 - e ] + u(x) [- e ] [ -2x/b]

50. Find the expected value of the DRV X with the p.m.f p(x) = 1/3, x = 0
2/3, x = 2.

Answer: Wkt, E(X) = x i p ( xi )

= 0.p(0) + 2. p(2)

n
= 0 (1/3) + 2( 2/3) = 4/3.

g.i
51. Prove that the function 𝒑(𝒙) is a legitimate probability mass function of a discrete random

rin
𝟐 𝟏 𝒙
( )
variable 𝑿, where 𝒑(𝒙) = { 𝟑 𝟑 , 𝒙 = 𝟎, 𝟏, 𝟐, . ..
𝟎, 𝒐𝒕𝒉𝒆𝒓𝒘𝒊𝒄𝒆
Answer: We have to prove ∑∞
2 1 𝑥
x=0 p(x) = 1.
2 1
ee
1 2 2 1 −1 2 3 −1
∑∞𝑥=0 𝑝(𝑥 ) = ∑∞𝑥=0 ( ) = [1 + + ( ) + ⋯ ] = (1 − ) = 3 (2) = 1.
3 3 3 3 3 3 3
gin
Therefore given 𝑝(𝑥 ) is a probability mass function of a random variable 𝑋.

52. Suppose that the duration 𝐗 in minutes of long distance calls from your home, follows
En

𝒙
𝟏
𝒆− 𝟓 , 𝒙 > 0
exponential law with p.d.f 𝒇(𝒙) = { 𝟓 what is 𝑷(𝑿 > 5) .
𝟎 , 𝒐𝒕𝒉𝒆𝒘𝒊𝒄𝒆
arn

𝑥
−1
Answer: Given, 𝑓 (𝑥 ) = 5 𝑒 5
𝑥 ∞
−
∞ ∞1 −𝑥 1 𝑒 5
𝑃 [ 𝑋 > 5] = ∫5 𝑓 (𝑥 )𝑑𝑥 = ∫5 5 𝑒 5 𝑑𝑥 = [ ] = −[𝑒 −∞ − 𝑒 −1 ] = 𝑒 −1 = 0.3679 .
5 −1⁄5
Le

5
w.
ww

10

www.LearnEngineering.in
www.LearnEngineering.in

UNIT – II
TWO DIMENSIONAL RANDOM VARIABLES

𝟏
1. If X and Y are random variables having the joint density function f(x,y) = (6 – x - y), 0 < x < 2,
𝟖
2 < y < 4, find P( X + Y < 3 ).
1
Answer: Given, f(x,y) = (6 - x - y), 0 < x < 2, 2 < y < 4
8
3 3 y
1
P(X + Y < 3) = 
2 0
8
(6  x  y )dxdy

3 y
= 1   6 x  x  xy  dy  1   y  6 y  27  dy =
3 2 3 2
5
8 2    .
2 0 8 2 2 2  3

n
g.i
𝟐. 𝑬(𝑿𝒀) = 𝑬(𝑿)𝑬(𝒀) if X and Y are ------------ variables.
Answer: Independent.

rin
3. Define Covariance.
Answer: A measure of association between two random variables obtained as the expected value of
the product of the two random variables around their means. i.e., Cov(X,Y) = E(XY) – E(X)E(Y).
ee
4. If X and Y are independent, then their covariance is ---------.
gin
Answer: zero.

5. Find the acute angle between the two lines of regression.

En

y 1y
Answer: The slopes of the regression lines are m1  r and m2 
x r x
If θ is the angle between the lines, then
arn

1
y r  x  y 1
m2  m1 r 
tan       r
1  m1 m2 x  y 
2
 x  y  r
2 2

Le

1   
x 
1−𝑟 2 𝜎𝑥𝜎𝑦
𝑡𝑎𝑛 𝜃 = (𝜎 ).
w.

𝑟 2 +𝜎 2
𝑥 𝑦

6. The regression lines of X on Y and Y on X are 𝟓𝒙 − 𝒚 = 𝟐𝟐, 𝟔𝟒𝒙 − 𝟒𝟓𝒚 = 𝟐𝟒 respectively.

ww

Find the means of X and Y.

Answer: Since both the lines of regression passes through the mean values x and y , the point
( x , y ) must satisfy the two regression lines.
Given, 5x – y = 22 ……….(1) and 64x - 45y = 24 ……….(2)
Solving (1) & (2) , we get
45 × (1) – (2)  161 x = 966  x = 6
Now (1)  30 – y = 22  y = 8.
Hence, mean of x = x = 6 , and mean of y = y = 8.

11

www.LearnEngineering.in
www.LearnEngineering.in

7. X and Y are independent random variables with variance 2 and 3. Find the variance of 3X+4Y.
Answer: Given that, X and Y are independent RVS with variance 2 and 3.
ie., Var(X) = 2,Var(Y) = 3 .
Var(3X+4Y) = 9Var(X) + 16 Var(Y) = 9 (2) +16 (3) = 66 .

8. The minimum and maximum values of the correlation coefficient are --- and -----.
Answer: -1 , 1.

9. The following table gives the joint probability distribution of X and Y. Find the (a) marginal
density function of X (b) marginal density function of Y.
Y/ X 1 2 3

n
1 0.1 0.1 0.2

g.i
2 0.2 0.3 0.1

Answer:

rin
Y/ X 1 2 3 P(Y = y)
1 0.1 0.1 0.2 0.4
2 0.2 0.3
ee 0.1 0.6
P(X= x) 0.3 0.4 0.3 1

The marginal density function of X and Y are

gin
X : 1 2 3 Y: 1 2
P(X = x) : 0.3 0.4 0.3 P(Y = y) : 0.4 0.6
En

10. If X and Y be integer valued random variables with P(X = m,Y = n) = q 2 pm+n-2,
n,m=1, 2, 3….. and p + q = 1. Are X and Y independent?
arn

Answer: If X and Y are independent , then P(X = m,Y = n) = P(X = m) P(Y = n) .....(1)
The marginal probability density function of X is given by
Le

 
 
P(X = m) =  q 2 p mn2 = q 2 p 2 p m  p n = q 2 p 2 p m p  p 2  p 3  ........
n 1 n 1

= q 2 p 2 p m p (1  p  p 2  ......) = q 2 p 2 p m p (1  p) 1
w.

= q 2 p 2 p m p q 1  qp m1 ...........(2)
ww

The marginal probability density function of Y is given by

 
 
P(Y = n) =  q 2 p mn2 = q 2 p 2 p n  p m = q 2 p 2 p n p  p 2  p 3  ........
m 1 m 1

= q 2 p 2 p n p (1  p  p 2  ......) = q 2 p 2 p n p (1  p) 1
= q 2 p 2 p n p q 1  qp n1 ...........(3)
Using (2) & (3), (1) becomes
P(X = m,Y = n) = qp m 1 . qp n1 = q2 pm+n-2.
Hence X & Y are independent.

12

www.LearnEngineering.in
www.LearnEngineering.in

11. When we say the two random variables are said to be orthogonal .
Answer:Their correlation is zero.

12. State the equations of the two regression lines.

𝜎
Answer: The line of regression of Y on X is given by y - 𝑦̅ = 𝑟. 𝜎𝑌 (𝑥 − 𝑥̅ )
𝑋
Where r is the correlation coefficient, 𝜎𝑋 𝑎𝑛𝑑 𝜎𝑌 are standard deviations.

𝜎
The line of regression of X on Y is given by x - 𝑥̅ = 𝑟. 𝜎𝑋 (𝑦 − 𝑦̅).
𝑌

13. If there is no linear correlation between two random variables X and Y, then what can you
say about the regression lines?.

n
Answer: If there is no linear correlation between X and Y, then r XY = 0.

g.i
Then the equations of the regression lines becomes 𝑦 = 𝑦̅ and 𝑥 = 𝑥̅ which are at right angles.

14. The two equations of the variables X & Y are x = 19.13 – 0.87y and y = 11.64 – 0.50x.

rin
Find the correlation coefficient between X & Y.
Answer: 𝜎𝑋𝑌 = −0.87 𝑎𝑛𝑑 𝜎𝑌𝑋 = −0.50
ee
𝑟 = −√𝜎𝑋𝑌. 𝜎𝑌𝑋 = − √(−0.87)(−0.50) = −0.6595.
gin
15. Write the properties of correlation coefficient.
Answer: i) Correlation coefficient does not exceed unity.
ii) When r = 1 the correlation is perfect and positive.
iii) Two independent variables are uncorrelated.
En

16. Give a real life example for each of positive correlation and negative correlation.
Answer:
arn

Example for positive correlation:

a)The heights and weights of a group of persons b) Income and expenditure.
Example for negative correlation:
Le

a)Price and demand of a commodity b) The correlation between volume and pressure of a
perfect gas.
w.

17. Let X and Y be two DRV’s with joint p.m.f P( X  x, Y  y)  1 / 18(2 x  y), x  1,2, y  1,2
 0 , elsewhere
ww

Find the marginal probability mass function of X and Y.

Answer:
Y/X 1 2 P(Y = y)
1 3/18 5/18 8/18
2 4/18 6/18 10/18
(PX = x) 7/18 11/18 1

13

www.LearnEngineering.in
www.LearnEngineering.in

Marginal probability mass function function of X & Y are given by

X : 1 2 Y : 1 2
P(X=x) : 7/18 11/18 P(Y = y) : 8/18 10/18

18. For λ > 0, let F(x,y) = 1 – λ e    x y  , if x > 0, y > 0 Check whether F can be the
0, otherwise joint probability distribution
function of two r.v’s X and Y.
Answer: Wkt, f(x,y) =  F ( x, y) =   e x e y    = 2 e y e x    = - 3 e  x e  y
2

xy x
  
 3 e x e y 
  e dxdy   {
3 x y
Now f ( x, y)dxdy  e } 0 dy

n
0 0 0 0 0


g.i
 
 e  y 
= - e e 2  y
dy     
 x 
    1.
2

   0
0

rin
0

Hence , given F can not be the joint probability distribution function of two r.v’s X and Y.

x x  y 
19. Let X and Y be CRV’s with joint p.d.f. f XY x, y  
ee 8
, 0 < x < 2 , -x < y < x

and f XY x, y  0 elsewhere. Find f Y / X  y / x .

gin
Answer: The marginal density function of X is given by
 x
1 xy 2 
 
x
1
f ( x)   f ( x, y ) dy   x 2  xy dy   x 2 y  
En

0
8 x 8 2  x
1  3 x 3   3 x 3  x3
  x      x    .
8  2   2  4
arn

x x  y 
x( x  y )
Wkt, f Y / X  y / x   f ( x, y) = 8
3
 .
f ( x) x 2x3
Le

4
20. The joint p.m.f of a 2D r.v (X,Y) is given by P(x,y) = K (2x+y); x = 1,2 and y = 1,2 where
K is a constant. Find K.
w.

Answer:
Y/ X 1 2 P(Y = y)
ww

1 3K 5K 8K
2 4K 6K 10
P(X= x) 7K 11K 18K

Wkt, Total probability = 1

i.e., 18K = 1  K  1 .
18

14

www.LearnEngineering.in
www.LearnEngineering.in

x2
21. The joint p.d.f. of a r.v (X,Y) is f XY x, y   xy 2  , 0 ≤ x ≤ 2, 0 ≤ y ≤ 1. Find P( X < Y ).
8
y
1 y
 2 x2   x2 y 2 x3 
1
Answer: P( X < Y ) = 0 0  xy  8  dxdy

  
0
2
  dy
24  0
1
=   y  y  dy   y  y   53 .
1 4 3 5 4

 2 24   10 96 
0    0 480
22. The joint p.d.f. of a r.v (X,Y) is given by f (x,y) = kxye  x  y2  ; x > 0, y > 0, find k.
2


Answer: Wkt,
  f ( x, y)dxdy  1
0 0

n
  

 kxye dxdy  1  k  xe dx  ye  y dy  1 ………..(1)

 x2  y2  x2 2
e

g.i
0 0 0 0
2
Let x = t  2 xdx  dt  xdx  dt / 2
Limits : when x  0 , t  0 & when x , t 

rin
  
 e t 
0 xe dx  0 e dt / 2    2   1 / 2
 x2 t

Now (1) becomes, k (1/2)(1/2) = 1

ee  k  4.
gin
23. Given the r.v X with density function f(x) = 2x , 0 < x < 1 Find the pdf of y = 8x 3.
0, elsewhere
Answer: Given, Y = 8x3
En

 1/ 3

Wkt , F(y) = P(Y ≤ y) = P( 8x3 ≤ y ) = P x  y 
 2 
y1 / 3 y1/ 3
arn

 
2 2 y1 / 3 1 2/3
=

0
f ( x)dx  
0
2 x dx  x 2 0
2

4
y

F(y) = 1 y 2 / 3
4
Le

d   1  2 
 f ( y)    F ( y )     y 2 / 3 1  1 / 6 y 1 / 3.
 dy   4  3 
w.

24. State the basic properties of joint distribution of (X,Y) when X and Y are r.v’s.
Answer:
ww

(i) F( ,  ) = 1 (ii) F(- ,   ) = 0, F(-  ,y) = 0 and F(x, -  ) = 0

(iii) 0 ≤ F(x,y) ≤ 1 (iv) F(x,  ) = F X (x) and F(  ,y) = F Y (y).

25. Can y = 5 + 2.8 x and x = 3 – 0.5 y be the estimated regression equations of y on x and x
on y respectively, explain your answer.
Answer:
Given the regression equation of y on x is y = 2.8 x + 5
 b yx = 2.8
Also given the regression equation of x on y is x = – 0.5 y + 3
15

www.LearnEngineering.in
www.LearnEngineering.in

 b xy = -0.5

Wkt, r = bxy .b yx = (0.5)(2.8) =  1.4 = Not possible, since -1 ≤ r ≤ 1.

Hence the given equations cannot be the regression equations of x on y and y on x
respectively.

26. The joint p.d.f. of the r.v x and y is defined as f(x,y) = 25 e 5 y , 0 < x < 0.2 , y > 0
0 , otherwise
Find the marginal PDFs of x and y.
Answer:The marginal p.d.f of X is


n
 
 e 5 y 
 f ( x, y) dy   25e
5 y
f(x) = dy  25    -5 (0 - 1) = 5.
  5 0

g.i
0 0

The marginal p.d.f of Y is

0.2 0.2

 f ( x, y) dx   25e dx  25e 5 y x0  25e 5 y (0.2)  5e 5 y .

rin
5 y 0.2
f(y) =
0 0

ee
27. Define the distribution function of two dimensional r.v (X,Y), state any one property.
Answer:
The distribution function of two dimensional r.v (X,Y) is defined as F(x,y) = P [ X ≤ x, Y ≤y).
gin
Property : (i) F( ,  ) = 1.
28. Define the joint pmf of a two dimensional DRV.
Answer: The function P ( X = x i , Y = y j ) = p xi , y j  is called the joint probability mass function
En

for DRV’s X and Y, provided the following conditions are satisfied (i) p ij  0  i, j
(ii)  p ij  1.
arn

j i

29. Let (X,Y) be a two dimensional r.v . Define the covariance of (X,Y). If X and Y are
independent what will be the covariance of (X,Y)?
Le

Answer:
The covariance of between X and Y is defined as Cov(X,Y) = E(XY) – E(X)E(Y).
If X and Y are independent , then Cov(X,Y) = 0. i.e., if X and Y are independent, then
w.

E(XY) = E(X)E(Y).
30. If the joint pdf of (X,Y) is 1 / 4, 0  x, y  2 find P( X+Y ≤ 1 ).
f ( x, y )  
 0 , elsewhere
ww

1 1 y 1 1 y 1

 f ( x, y) dxdy   1 / 4 dxdy  1 / 4 x0 dy

1 y
Answer: P( X+Y ≤ 1 ) =
0 0 0 0 0
1
= ¼  (1  y )dy  1  y  y   1 . 1  1 .
1 2

0
4 2 0 4 2 8

31. Find the marginal density functions of X and Y if

6 / 5( x  y 2 ), 0  x  1, 0  y  1
f ( x, y)  
 0 , elsewhere
Answer:
16

www.LearnEngineering.in
www.LearnEngineering.in

The marginal density function of X is

1
6 y3  6 1
1 1
6
f ( y)  
0
f ( x, y) dy   ( x  y 2 ) dy   xy     x  .
0
5 5 3 0 5  3
The marginal density function of Y is
1
6  x2  6 1
1 1
6
f ( y)  
0
f ( x, y ) dx   ( x  y 2 ) dx  
0
5 5 2
 xy 2    y 2  .
0 5  2
32. Types of Correlation
Answer: There are 3 important ways of classifying correlation:
(i)Positive and Negative : If the two variables deviate in the same direction i.e., if the increase
in one variable results in a corresponding increase in the other or if the decrease in one variable
results in a corresponding decrease in the other, then the correlation said to be positive.

n
Ex: The correlation between the height and weight of a person.

g.i
If the two variables constantly deviate in the opposite direction i.e., if the increase in one
variable results in a corresponding decrease in the other or if the decrease in one variable results
in a corresponding increase in the other, then the correlation is said to be negative.

rin
Ex: The correlation between the volume and pressure of a perfect gas.

(ii) Simple, Partial and Multiple : If only two variables are considered for correlation analysis,
ee
it is called a simple correlation.
In a multiple correlation, three or more variables are studied simultaneously.
gin
Ex: The study of relationship between the yield of rice per hectare and both the amount of
rainfall and the usage of fertilizers is a multiple correlation.
When three or more variables are involved in correlation analysis, the correlation between the
En

dependent variable and only one particular independent variable is called partial correlation.

(iii) Linear and Non-linear : If the amount of change in one variable tends to bare a constant
arn

ratio to the amount of change in the other variable, then the correlation is said to be linear.
A correlation is said to be non-linear if the amount of change in one variable does not bare
a constant ratio to the amount of change in the other variable.
Le

Ex: If rainfall is doubled, the production of rice would not necessarily be doubled.
33. Distinguish between Correlation and regression analysis.
Answer:
w.

Correlation Regression
Correlation means relationship Regression is a mathematical measure of
ww

between two variables. expressing the average relationship between the

two variables.
Correlation need not imply cause and Regression analysis clearly indicates the cause
effective relationship between the and effective relationship between the variables.
variables.
Correlation coefficient is symmetric Rgression coefficient is not symmetric
i.e., rxy  ryx i.e., bxy  b yx
Correlation coefficient is a measure of Using the relationship between two variables we
the direction and the degree of linear can predict the dependent variable value for any
relationship between two variables. given independent variable value.
17

www.LearnEngineering.in
www.LearnEngineering.in

34. Methods of studying Correlation:

Answer: (i) Scatter diagram method (ii) Graphical method (iii) Rank method
(iv) Concurrent deviation method (v) Karl pearson’s co-efficient of correlation (vi) Method of
least squares.

35. The regression equations are 𝟑𝒙 + 𝟐𝒚 = 𝟐𝟔, 𝟔𝒙 + 𝒚 = 𝟑𝟏. Find the means of X and Y.
Answer: Since both the lines of regression passes through the mean values x and y , the point
( x , y ) must satisfy the two regression lines
Given, 3𝑥 + 2𝑦 = 26 ……….(1) 6𝑥 + 𝑦 = 31 ……….(2)
Solving (1) & (2) , we get
2 × (1) – (2)  3 y = 21  y = 7

n
Now (1)  3x = 12  x = 4.

g.i
Hence, mean of x = x = 4 , and mean of y = y = 7.
36. Find the value of 𝒌, if 𝒇(𝒙, 𝒚) = 𝒌(𝟏 − 𝒙)(𝟏 − 𝒚) in 𝟎 < 𝑥, 𝑦 < 1 and 𝒇(𝒙, 𝒚) = 𝟎, otherwise, is

rin
to be the joint density function.
Answer:
We know that 𝑓 (𝑥, 𝑦) satisfies the condition.
∞ ∞ ee
∫−∞ ∫−∞ 𝑓(𝑥, 𝑦) 𝑑𝑦 𝑑𝑥 = 1
1 1
∫0 ∫0 𝑘(1 − 𝑥 )(1 − 𝑦) 𝑑𝑦 𝑑𝑥 = 1
gin
1 𝑦2 1
𝑘 ∫0 (1 − 𝑥 )[𝑦 − ] 𝑑𝑥 = 1
2 0
𝑘 1
∫ (1 − 𝑥 ) 𝑑𝑥
2 0
=1
En

𝑘 𝑥2 1
[𝑥 − ] =1
2 2 0
𝑘
=1
4
arn

𝑘 = 4.

37. Assume that the random variables 𝑿 𝒂𝒏𝒅 𝒀 have the probability density function 𝒇(𝒙, 𝒚).
What is 𝑬[𝑬(𝑿⁄𝒀)] ?
Le

Answer:
If 𝑋 𝑎𝑛𝑑 𝑌 are independent random variables, than
w.

i. 𝐸 [𝐸 (𝑋⁄𝑌)] = E[X]
ii. 𝐸 [𝐸 (𝑌⁄𝑋)] = 𝐸[𝑌]
ww

38. If 𝑿, 𝒀 denote the deviation of variance from the arithmetic mean and if 𝝆 = 𝟎. 𝟓, ∑ 𝑿𝒀 =
𝟏𝟐𝟎; 𝝈𝒚 = 𝟖; ∑ 𝑿𝟐 = 𝟗𝟎, Find 𝒏, the number of times.
Answer:
Given 𝑋 = 𝑥 − 𝑥̅ , 𝑌 = 𝑦 − 𝑦̅
1 1
∑(𝑥−𝑥̅ )(𝑦−𝑦̅) ∑ 𝑋𝑌
𝑛 𝑛
𝜌= 1 1
= 1
√ ∑(𝑥−𝑥̅ )2 √ ∑(𝑦−𝑦̅)2 √ ∑ 𝑋 2 √𝜎𝑦2
𝑛 𝑛 𝑛
1
(120) 120
𝑛
0.5 = 1 √𝑛 = 9.48×8×0.5 = 3.16 𝑛 = 10.
(9.48)(8)
√𝑛

18

www.LearnEngineering.in
www.LearnEngineering.in

UNIT – III
RANDOM PROCESSES
1. Define wide sense stationary process.
Answer:
A random process {X(t)} is called WSS if mean is a constant and the auto correlation
depends only on the time difference.
2. Define a Markov chain.
Answer:
If { X n  an / X n1  an1 , X n2  an2 , ...., X 0  a0 }  P { X n  an / X n1  an1 } for all n,
then the process X(t) is called as Markov chain. Here a 0 , a1 ,…, an are called the states of the
Markov chain.

n
g.i
3. State any two properties of Poisson process.
Answer:

rin
i) The Poisson process is a Markov process.
ii) The sum of two independent Poisson processes is a Poisson process.
iii) The difference of two independent Poisson processes is not a Poisson process.
ee
4. Prove that the difference of two independent Poisson processes is not a Poisson process.
Answer:
gin
Let X(t) = X1(t) – X2(t), E[X(t)] = E[X1(t)] – E[X2(t)]  E[X(t)] = (𝜆1– 𝜆 2)t

E(X2(t)] = E { X 12(t) + X 22(t) - 2 X1(t) X2(t) } = 12 t 2  2 2 t 2  212  1t  2 t
E(X2(t)] ≠( 𝜆1 − 𝜆2 )(𝑡) + ( 𝜆1 − 𝜆2 )2 𝑡 2
En

 the difference of two independent Poisson processes is not a Poisson process.

arn

5. State the postulates of a poisson process.

Answer:
Let X (t) = number of times an event occurred upto time ‘t’ so that the sequence
{𝑋(𝑡), 𝑡 ∈ [0, ∞)} forms a poisson process with parameter ‘𝜆′ .
Le

i) Events occurring in non-overlapping intervals are independent of each other

ii) P[X(t) = 1 for t in (x, x+h)] = 𝜆h + o(h)
w.

iii) P[X(t) = 0 for t in (x, x+h)] =1 - 𝜆h + o(h)

iv) P[X(t) = 2 or move for t in (x, x+h)] = o(h).
ww

6. Define Strict Sense Stationary processes (or) stationary process.

Answer:
A random process X(t) is called SSS, if its statistical characteristics do not change with time.
i.e., E[X(t)] = constant & Var[X(t)] = constant.

7. State Chapman – Kolmorgow theorem.

Answer:
If ‘p’ is the tpm of a homogeneous Markov chain, then the n-step tpm P(n) is equal to Pn
(𝑛) 𝑛
𝑖. 𝑒., [𝑃𝑖𝑗 ] = [𝑃𝑖𝑗 ] .

19

www.LearnEngineering.in
www.LearnEngineering.in

8. Define I & II order stationary Process.

Answer:
I Order Stationary Process: A random process X(t) is said to be first order stationary process,
if E[X(t)] is constant.
II Order Stationary Process: A random process X(t) is said to be second order stationary
process,
if E[X(t)] & E[X2(t)] are constants.

9. If the transition probability matrix of a markov chain is 0 1 find the steady-state distribution
1 1
 
2 2
of the chain.

n
Answer:
2 2

g.i
By the property  p    (1 ,  2 )  10 1
1 = (1 ,  2 )  = 1 & 1 + = 2
  2 2
2 2
Wkt, 1   2  1 ......(1) , replace  2 = 1 in (1) , we get  2 = 2 .

rin
2 3
10. Prove that a first order stationary process has a constant mean.
Answer: ee
Let X(t) be a first order stationary random process.
 f (x, t + ɛ) = f(x, t) ……….(1) where t , ɛ are arbitrary.
gin
 
E[X(t + ɛ )] =  x f ( x, t   ) dx =

 x f ( x, t ) dx

by (1)

= E[X(t)] = constant.
En

11. Consider the random process X(t) = cos(t+φ) where φ is a random variable with density
function f(φ) = 1/π, - π/2 < φ < π/2, check whether the process is stationary or not.
arn

Answer:

 2 2 cos t
   1
E[X(t)] = =
 cos(t   )  d = 
Le

x (t ) f ( ) d
2

E[X(t)] is not a constant  X(t) is not a stationary.

w.

12. Show that the random process X(t) =A sin(wt+φ), where A and w are constants,
ww

φ is random variable uniformly distributed in (0, 2𝝅) is first order stationary.

Answer:
 2
1
E[X(t)] =


 x(t ) f ( )d = A sin( wt   )
0
2
d = 0

E[X(t)] = constant.  X(t) is a first order stationary.

13. Define Ergodic process.

Answer:
A random process X(t) is called ergodic if its time averages are equal to ensemble averages.

20

www.LearnEngineering.in
www.LearnEngineering.in

14. Define irreducible Markov chain?

Answer :
If Pij (𝑛) ≥ 0 for some n and for all i & j, then every state can be reached from every other
state. When this condition is satisfied, the Markov chain is said to be irreducible.

15. Show that the auto correlation function of a stationary process {X(t)} is a even function.
Answer :
We know that RXX ( )  E[ X (t ) X (t   )]
Replace  by -  , we get RXX ( )  E[ X (t ) X (t   )]
Put t - τ = t1  t = t1 + τ.
RXX ( )  E[ X (t1 ) X (t1   )] = RXX ( ) . Hence RXX ( ) is an even function.

n
g.i
16. When is a Poisson process said to be homogeneous?
Answer:
The rate of occurrence of the event  is a constant, then the process is called a homogeneous

rin
poisson process.

17. If the customers arrive at a bank according to a Poisson process with a mean rate of 2 per
ee
minute, find the probability that, during a 1- minute interval no customer arrives.
Answer:
gin
 t
Given   2 & t  1, P[ X (t )  n]  e (t ) n 
P[ X(t) = 0 ] = e-2
n!

18. When are the process {X( t)} & { Y( t)} said to be jointly stationary in the wide sense?
En

Answer:
Two random process {X( t)} & { Y( t)} are said to be jointly stationary in the wide sense,
if each process is individually a WSS process and R XY (t1 , t 2 ) is a function of (t1 – t2) only.
arn

19. Prove that the sum of two independent Poisson processes is again a Poisson process.
Answer:
Le

Let 𝑋 (𝑡) = X1 (t) + X 2 (t)

 t
n 
e  1 t (1t ) r e 2 (2 t ) n r
P[X(t) = n] =  [ P[ X 1 (t )  r ]{P [ X 2 (t )  n  r ] =  (n  r )!
w.

r 0 r 0 r!
 ( 1  2 ) t n  ( 1  2 ) t
= e  n Cr 1t  2t  1t  2 t  n
nr e

r

n! r 0 n!
ww

 X1(t) + X2(t) is a poisson process with parameter 1  2 .

20. Define stochastic processes (or) Define random process and give an example.
Answer:
A random process is a collection of random variables {X(s, t)} that are functions of a real
variable, namely time t where s ϵ S (sample space) and t ϵ T(parameter set).
Example: (i) The daily stock price, (ii) The wireless signal received by a cell phone over time.

21. Consider the random process X(t) = cos(w0 t + θ) with θ uniformly distributed in the

21

www.LearnEngineering.in
www.LearnEngineering.in

interval (-π, π), check whether x(t) is stationary or not.

Answer:
Given, f(θ) = 1 , -π < θ < π.
2

E [X (t)] = 1  cosw0 t    d = 0 = constant.
2 

E[X2(t)] = E[ cos2(w0t + θ)] = 1 E[ 1 + cos(2 w0 t  2 ) ] = 1 + cos(2w0t  2 ) 1 d
2  2 
2

= 1 +0= 1.
2 2
Var[X(t)] = E[X (t)] – { E [X(t)]} = ½ -0 = ½ = constant.
2 2

Hence X(t) is a stationary process.

n
g.i
22. Give an example of evolutionary random process.
Answer:

rin
Example for evolutionary process is Poisson process.

23. Define a semi – random telegraph signal process.

Answer: ee
If N(t) represents the number of occurrences of a specified event in (0,t) and X(t) =  1N ( t ) ,
then {X(t)} is called a semi – random telegraph signal process.
gin

24. Let A =  0 1 

 be a stochastic matrix. Check whether it is regular.
1 / 2 1 / 2 
En

Answer:
A2 =  0 1  0
 
1  1 / 2 1 / 2 
 =  
arn

1 / 2 1 / 2  1 / 2 1 / 2  1 / 4 3 / 4 
All the entries of A2 are positive. Hence the given matrix is regular.

25. If the customers arrive at a bank according to a Poisson process with mean rate 2 per minute,
Le

find the
probability that during a 1- minute interval no customers arrives.
w.

Answer:
Let 𝑋(𝑡) be the no. of customers arrive at a bank.
Mean =  = 2 per min
ww

Time 𝑡 = 1 per min

𝑒 −𝑡 (𝑡)𝑛
𝑋(𝑡) follows Poisson process, 𝑃[𝑋(𝑡) = 𝑛] = .
𝑛!
𝑒 −2(2)0
P[ No customers arrives in 1- minute interval ]= 𝑃 [𝑋(1) = 0] = = 𝑒 −2 = 0.135.
0!

UNIT - IV

22

www.LearnEngineering.in
www.LearnEngineering.in

CORRELATION AND SPECTRAL DENSITIES

1. Find the power spectral density function of the stationary process whose auto - correlation
function is given by e   .
Answer:
Given, RXX ( ) = e   . The power spectral density function is given by
 

 R XX ( )e d  e
iw 
S XX ( )  e iw d
 
0 

 e e d  e
 iw 
 e iw d

n
 0
0 

e d   e  (1i ) d

g.i
  (1i ) .
 0
0 
 e (1i )   e  (1i )  1 1
  (1i )    (1i )   (1  0)  ((0  1)

rin
    0 1  i  (1  i )
1 1 2
   .
1  i 1  i ee 1 2
-  .
2. Find the power spectral density of a random signal with autocorrelation function e
gin
Answer:
 

 R XX ( )e d  e
iw  
S XX ( )  e iw d
 
En

0 

 e e d  e
 iw  iw
 e d
 0
0 
.
e d   e  (  i ) d
 (   i )

arn

 0

 (   i ) 0 
e   e  (  i )  1 1
  (  i )    (  i )   (1  0)  ((0  1)
    0   i  (   i )
Le

1 1 2
   2 .
  i   i  2
w.

3. If the auto correlation function for a stationary ergodic process with no periodic component is
4
R XX ( )  25  .Find the mean.
1  6 2
ww

Answer:
2 4
We know that , X   lim  R XX ( )   lim  25   25
1  6 2
 X  5 i.e., mean = E[X(t)] = 5.

4. Find the variance of the stationary process {X(t)} whose auto correlation function is

23

www.LearnEngineering.in