UNIT-II

Probability Distribution

Random Variables:
In a random experiment, if a real variable is associated with every outcome then it is called a
random experiment or stochastic variable.

In other words a random variable is a function that assigns a real number to every sample
point in the sample space of a random experiment.

Random variables are usually denoted by X, Y, Z…. and it may be, different random variables
may be associated with the same sample space S.
The set of all real numbers of a random variable X is called the range of X.

Example -1: While tossing a coin, suppose that the value 1 is associated for the outcome head and
0 for the outcome tail.
We have the sample space 𝑆 = {𝐻, 𝑇}
And if X is the random variable then 𝑋(𝐻) = 1 & 𝑋(𝑇) = 0
Range of 𝑋 = {0,1}
Example-2: Suppose a coin is tossed twice, we shall associate two different random variables X,
Y as follows
Then we have the sample space 𝑆 = {𝐻𝐻, 𝐻𝑇, 𝑇𝐻, 𝑇𝑇}
𝑋 = Number of heads in the outcome.
The association of the elements in 𝑆 𝑡𝑜 𝑋 is as follows.
Out come 𝐻𝐻 𝐻𝑇 𝑇𝐻 𝑇𝑇
Random variable X 2 1 1 0
Range of 𝑋 = {0,1,2}
Suppose Y= Number of tails in the outcome.
Out come 𝐻𝐻 𝐻𝑇 𝑇𝐻 𝑇𝑇
Random variable Y 0 1 1 2
Range of 𝑌 = {0,1,2}
Discrete and Continuous random variables – Definitions

If a random variable takes finite or countably infinite number of values the it is called a
discrete random variable.
Here countably infinite means a sequence of real numbers.
Example:
a) Tossing a coin and observing the outcome.
b) Throwing a die and observing the numbers on the face.

If a random variable takes infinite or non-countable infinite number of values the it is

called a non - discrete random variable or Continuous random variables.
Example:
a) Weight of articles.
b) Conducting a survey on the life of electric bulbs.

I. Discrete Probability Distribution:

Definition: If for each 𝑥𝑖 of a discrete random variable X, we assign a real number 𝑃(𝑥𝑖 )
such that
𝑖) 𝑃(𝑥𝑖 ) ≥ 0
𝑖𝑖) ∑𝑖 𝑃(𝑥𝑖 ) = 1
Then the function 𝑃(𝑥) is called a probability function

If the probability that X takes the values 𝑥𝑖 𝑖𝑠 𝑝𝑖 then

𝑃(𝑋 = 𝑥𝑖 ) = 𝑝𝑖 𝑜𝑟 𝑝(𝑥𝑖 )

The set values [𝑥𝑖 , 𝑝(𝑥𝑖 )] is called a discrete (finite) probability distribution of the discrete
random variable X.
The function 𝑃(𝑋) is called the probability density function (𝑝. 𝑑. 𝑓) or the probability mass
function (𝑝. 𝑚. 𝑓)

The distribution function 𝑓(𝑥) defined by

𝑓(𝑥) = 𝑃(𝑋 ≤ 𝑥) = ∑𝑥𝑖=1 𝑝(𝑥𝑖 ) 𝑥 being an integer is called cumulative distribution function
(𝑐. 𝑑. 𝑓)
 The Mean and Variance of the discrete probability distribution is defined as follows.

Mean (𝜇) = ∑𝑖 𝑥𝑖 𝑝(𝑥𝑖 )

Variance (𝑉) = ∑𝑖 (𝑥𝑖 − 𝜇)2 𝑝(𝑥𝑖 )

Or Variance (𝑉) = ∑𝑖 𝑥𝑖 2 𝑝(𝑥𝑖 ) − (∑𝑖 𝑥𝑖 𝑝(𝑥𝑖 ))2

Variance (𝑉) = ∑𝑖 𝑥𝑖 2 𝑝(𝑥𝑖 ) − (𝜇)2

S.D (𝜎) = √𝑉

Problem-1: A coin tossed twice. A random variable X represent the number of heads turning up.
Find the discrete probability distribution for X. Also find mean and variance.

Solution: Sample Space 𝑆 = {𝐻𝐻, 𝐻𝑇, 𝑇𝐻, 𝑇𝑇}

Random variable 𝑋 = (2,1,1,0)
1 1 1 1
Now, 𝑃(𝐻𝐻) = 4, 𝑃(𝐻𝑇) = 4, 𝑃(𝑇𝐻) = 4, 𝑃(𝑇𝑇) = 4,
1
𝑃 (𝑋 = 0, 𝑖. 𝑒. 𝑛𝑜 ℎ𝑒𝑎𝑑 ) = 𝑃(𝑇𝑇) = 4
2 1
𝑃 (𝑋 = 1, 𝑖. 𝑒. 𝑜𝑛𝑒 ℎ𝑒𝑎𝑑 ) = 𝑃(𝐻𝑇 𝑈 𝑇𝐻) = 𝑃(𝐻𝑇) + 𝑃(𝑇𝐻) = 4 = 2
1
𝑃 (𝑋 = 2, 𝑖. 𝑒. 𝑇𝑤𝑜 ℎ𝑒𝑎𝑑 ) = 𝑃(𝐻𝐻) = 4

The Discrete probability distribution for X is as follows

𝑋 = 𝑥𝑖 0 1 2
𝑝(𝑥𝑖 ) ¼ ½ ¼

Here 𝑖) 𝑃(𝑥𝑖 ) ≥ 0 and 𝑖𝑖) ∑𝑖 𝑃(𝑥𝑖 ) = 1

Mean (𝜇) = ∑𝑖 𝑥𝑖 𝑝(𝑥𝑖 )

1 1 1
Mean (𝜇) = ∑ 𝑥 𝑝(𝑥) = 0 (4) + 1 (2) + 2 (4) = 1

Variance (𝑉) = ∑𝑖 (𝑥𝑖 − 𝜇)2 𝑝(𝑥𝑖 )

(0−1)2 1 1 1 1
Variance (𝑉) = ∑(𝑥 − 𝜇)2 𝑝(𝑥) = + (1 − 1)2 2 + (2 − 1)2 4 = 2
4

1
Mean (𝜇) = 1 and Variance (𝑉) = 2
Problem-2: Show that the following distribution represents a discrete probability distribution.
Find mean and variance.
x 10 20 30 40
p(x) 1/8 3/8 3/8 1/8
1 3 3 1
Solution: We observed that 𝑖) 𝑃(𝑥𝑖 ) ≥ 0 and 𝑖𝑖) ∑𝑖 𝑃(𝑥𝑖 ) = 8 + 8 + 8 + 8 = 1

Mean (𝜇) = ∑ 𝑥 𝑝(𝑥)

1 3 3 1
= 10 ( ) + 20 ( ) + 30 ( ) + 40 ( )
8 8 8 8

= 25

Variance(𝑉) = ∑(𝑥 − 𝜇)2 𝑝(𝑥)

(10 − 25)2 3 3 1
= + (20 − 25)2 + (30 − 25)2 + (40 − 25)2
8 8 8 8

𝑉 = 75

Problem-3: Find the value of k such that the following distribution represents a finite probability
distribution. Hence find its mean and standard deviation. Also find 𝑝(𝑋  1), 𝑝(𝑋 > 1) and
𝑝(−1 < 𝑋  2).

x -3 -2 -1 0 1 2 3
p(x) k 2k 3k 4k 3k 2k k
Solution: We must have 𝑃(𝑥) ≥ 0

∑𝑖 𝑃(𝑥𝑖 ) = 𝑘 + 2𝑘 + 3𝑘 + 4𝑘 + 3𝑘 + 2𝑘 + 𝑘 = 1

1
16𝑘 = 1 ∴ 𝑘 = 16

Discrete probability distribution is

x -3 -2 -1 0 1 2 3
p(x) 1/16 2/16 3/16 4/16 3/16 2/16 1/16

Mean (𝜇) = ∑ 𝑥 𝑝(𝑥)

1 2 3 3 2 1
= −3 ( ) − 2 ( ) − 1 ( ) + 0 + 1 ( ) + 2 ( ) + 3 ( )
16 16 16 16 16 16
=0
 Variance(𝑉) = ∑(𝑥 − 𝜇)2 𝑝(𝑥)

(−3 − 0)2 2 3 4 3 2
= + (−2 − 0)2 + (−1 − 0)2 + (0 − 0)2 + (1 − 0)2 + (2 − 0)2
16 16 16 16 16 16
1
+ (3 − 0)2
16

40 5
𝑉 = =
16 2

Thus, i) 𝑃(𝑋  1) = 𝑝(−3) + 𝑝(−2) + 𝑝(−1) + 𝑝(0) + 𝑝(1) = 13/16

1 2 3 4 1
= 16 + 16 + 16 + 16 + 16 = 13/16

2 1 3
ii) 𝑝(𝑋 > 1) = 𝑝(2) + 𝑝(3) = 16 + 16 = 16

4 3 2 9
iii) 𝑃(−1 < 𝑋  2) = 𝑝(0) + 𝑝(1) + 𝑝(2) = 16 + 16 + 16 = 16

Problem-3: The probability density function of a variable X is given by the following table

x 0 1 2 3 4 5 6
p(x) k 3k 5k 7k 9k 11k 13k
For what value of K, this represents a valid probability distribution? Also find
(𝑖) 𝑃(𝑋 ≥ 5) (𝑖𝑖) 𝑃(3 < 𝑋  6)

Solution: The probability distribution is valid if 𝑃(𝑥) ≥ 0 and ∑𝑖 𝑃(𝑥𝑖 ) = 1

∴ ∑𝑖 𝑃(𝑥𝑖 ) = 𝑘 + 3𝑘 + 5𝑘 + 7𝑘 + 9𝑘 + 11𝑘 + 13𝑘 = 1

1
49𝑘 = 1 ∴ 𝑘 = 49

Discrete probability distribution is

x 0 1 2 3 4 5 6
p(x) 1/49 3/49 5/49 7/49 9/49 11/49 13/49

11 13 24
(𝑖)𝑃(𝑋 ≥ 5) = 𝑝(5) + 𝑝(6) = + =
49 49 49
9 11 13
(𝑖𝑖)𝑃(3 < 𝑋  6) = 𝑝(4) + 𝑝(5) + 𝑝(6) = + + = 33/49
49 49 49
Problem-4: Find the value of the constant k and the mean and the variance of the following
distribution. Also find 𝑃(𝑋 > −1)

x -2 -1 0 1 2 3
p(x) 0.1 k 0.2 2k 0.3 k

Solution: The probability distribution is valid if 𝑃(𝑥) ≥ 0 and ∑𝑖 𝑃(𝑥𝑖 ) = 1

∴ ∑𝑖 𝑃(𝑥𝑖 ) = 0.1 + 𝑘 + 0.2 + 2𝑘 + 0.3 + 𝑘 = 1

4𝑘 + 0.6 = 1 ∴ 4𝑘 = 1 − 0.6 = 0.4

∴ 𝑘 = 0.1

Discrete probability distribution is

x -2 -1 0 1 2 3
p(x) 0.1 0.1 0.2 0.2 0.3 0.1

Mean (𝜇) = ∑ 𝑥 𝑝(𝑥)

= −2(0.1) − (0.1) + 0 + 0.2 + 2(0.3) + 3(0.1)
= 0.8

Variance(𝑉) = ∑(𝑥 − 𝜇)2 𝑝(𝑥) = 2.16

Also 𝑃(𝑋 > −1) = 𝑝(0) + 𝑝(1) + 𝑝(2) + 𝑝(3) = 0.2 + 0.2 + 0.3 + 0.1 = 0.8

Problem-5:A random variable X has the following probability distribution function for various
values of x

x 0 1 2 3 4 5 6 7
p(x) 0 k 2k 2k 3k k2 2k2 2
7k + k
Find (1) k (ii) P(X < 6) (iii) P(X  6).
Bernoullis Theorem:

The probability of x successes in n trials is equal to 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥 where p is the probability of
success and q is the probability of failure.

Remarks: Bernoulli’s theorem leads to Binomial Distribution and limiting case of this distribution
leads to Poisson Distribution. These are Discrete Probability Distributions

1. Binomial Distribution:

If 𝑝 is the probability of success and 𝑞 is the probability of failure, the probability of 𝑥 successes
out of n trials is given by 𝑃(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥
The probability distribution of [𝑥, 𝑃(𝑥)] 𝑖𝑠
𝑋 = 𝑥𝑖 0 1 2 ……. n
𝑛 1 𝑛−1 2 𝑛−2
𝑝(𝑥𝑖 ) 𝑞 𝑛𝐶1 𝑝 𝑞 𝑛𝐶2 𝑝 𝑞 ……. 𝑝𝑛

It may be observed that the value of 𝑃(𝑥) for different values 𝑥 = 0,1,2,3 … … are the successive
terms in the binomial expansion of (𝑝 + 𝑞)𝑛 and accordingly this distribution is called the
Binomial Distribution or Bernoullis Distribution
∑ 𝑃(𝑥) = 𝑞 𝑛 + 𝑛𝐶1 𝑝1 𝑞 𝑛−1 + 𝑛𝐶2 𝑝2 𝑞 𝑛−2 + ⋯ … + 𝑝𝑛 = (𝑝 + 𝑞)𝑛 = (1)𝑛 = 1
Hence 𝑃(𝑥) is a probability function

The Mean and S.D of the Binomial Distribution:

Mean (𝜇) = ∑𝑖 𝑥𝑖 𝑝(𝑥𝑖 )

Mean (𝜇) = ∑ 𝑥 𝑝(𝑥) = 𝑛𝑝

Variance (𝑉) = ∑𝑖 𝑥𝑖 2 𝑝(𝑥𝑖 ) − (∑𝑖 𝑥𝑖 𝑝(𝑥𝑖 ))2

Variance (𝑉) = ∑ 𝑥 2 𝑝(𝑥) − (𝜇)2

Variance (𝑉) = 𝑛𝑝𝑞

S.D (𝜎) = √𝑉 = √𝑛𝑝𝑞

Mean (𝜇) = 𝑛𝑝, Variance (𝑉) = 𝑛𝑝𝑞, S.D (𝜎) = √𝑛𝑝𝑞

 2) Poisson Distribution:
Poisson distribution is regarded as the limiting form of the binomial distribution when 𝑛
is very large (𝑛 → ∞) and 𝑝 the probability of success is very small (𝑝 → 0) so that 𝑛𝑝 tends
to a fixed finite constant say 𝑚

𝑚𝑥 𝑒 −𝑚
Poisson distribution of the random variable is 𝑃(𝑥) = 𝑥!

𝑃(𝑥) is also called Poisson probability function and x is called a Poisson variate. The
distribution of probabilities for 𝑥 = 0, 1, 2, 3, … …. Is as follows
𝑋 = 𝑥𝑖 0 1 2 3 4 ……..
−𝑚 1 −𝑚 2 −𝑚 3 −𝑚 4 −𝑚
𝑝(𝑥𝑖 ) 𝑒 𝑚 𝑒 𝑚 𝑒 𝑚 𝑒 𝑚 𝑒 … ….
1! 2! 3! 4!

We have 𝑃(𝑥) ≥ 0 and

𝑚1 𝑒 −𝑚 𝑚2 𝑒 −𝑚 𝑚3 𝑒 −𝑚
∑∞
𝑥=0 𝑃(𝑥) = 𝑒
−𝑚
+ + + … … … … ..
1! 2! 3!
𝑚1 𝑚2 𝑚3
= 𝑒 −𝑚 {1 + + + …………..}
1! 2! 3!

= 𝑒 −𝑚 𝑒 𝑚 = 1

The Mean and S.D of the Poisson Distribution:

Mean (𝜇) = ∑𝑖 𝑥𝑖 𝑝(𝑥𝑖 )

Mean (𝜇) = ∑ 𝑥 𝑝(𝑥) = 𝑚

Variance (𝑉) = ∑𝑖 𝑥𝑖 2 𝑝(𝑥𝑖 ) − (∑𝑖 𝑥𝑖 𝑝(𝑥𝑖 ))2

Variance (𝑉) = ∑ 𝑥 2 𝑝(𝑥) − (𝜇)2

Variance (𝑉) = 𝑚

S.D (𝜎) = √𝑉 = √𝑚
Mean (𝜇) = 𝑚, Variance (𝑉) = 𝑚, S.D (𝜎) = √𝑚
Problem-1: In 800 families with 5 children each how many families would be expected to have
(i) 3 boys (ii) 5 girls (iii) either 2 or 3 boys (iv) at most 2 girls by assuming probability for boys
and girls to be equal.
Solution: 𝑝 = probability of having a boy= 1/2, 𝑞 = probability of having a girl= 1/2
Let 𝑥 denote the number of boys in the family.
Binomial Distribution function 𝑃(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥 where 𝑛 = 5
1 𝑥 1 5−𝑥
𝑖. 𝑒. 𝑃(𝑥) = 5𝐶𝑥 ( ) ( )
2 2
1 1
𝑖. 𝑒. 𝑃(𝑥) = 5 5𝐶𝑥 = 5
2 32 𝐶𝑥
𝑆𝑖𝑛𝑐𝑒 we have to find the expected number in respect of 800 families, We
1
have 800 𝑃(𝑥) = 800 5𝐶𝑥 = 𝑓(𝑥)
32

𝑓(𝑥) = 25 5𝐶𝑥 = 𝑓(𝑥)

i) Expected to have 3 boys
(we have to find 𝑓(3))
𝑓(3) = 25 5𝐶3 = 25 × 10 = 250
Expected number of families with 3 boys is 250
ii) we have to find f(0)
𝑓(0) = 25 5𝐶0 = 25 × 1 = 25
Expected number of families with no boys (5 girls) is 25
iii) We have to find 𝑓(2) + 𝑓(3)
= 25 5𝐶2 + 25 5𝐶3
= 50 5𝐶2 = 50 × 10 = 500
Expected number of families with either 2 or 3 boys is 500
iv) At most 2 girls means that,
families can have 5 boys and 0 girls or 4 boys and 1 girl or 3 boys and 2 girls
Hence we have to find 𝑓(5) + 𝑓(4) + 𝑓(3)
= 25 5𝐶5 + 25 5𝐶4 + 25 5𝐶3
= 25 (1 + 5 + 10) = 25 × × 16 = 400
Expected number of families with at most 2 girls is 400
Problem-2: In a sampling a large number of parts manufactured by a machine, the mean number
of defectives in a sample of 20 is 2. Out of 1000 such samples, how many would be expected to
contain at least 3 defective parts?
Solution: We have 𝑃(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥
By data Mean (𝜇) = 𝑛𝑝 = 2, 𝑤ℎ𝑒𝑟𝑒 𝑛 = 20
1
20 𝑝 = 2 ∴ 𝑝 = 10 = 0.1, 𝑞 = 1 − 𝑝 = 1 − 0.1 = 0.9

∴ 𝑃(𝑥) = 20𝐶𝑥 (0.1)𝑥 (0.9)20−𝑥

Let 𝑥 denote the defective part.
We have to find probability of atleast 3 defective parts = 𝑃(𝑥 ≥ 3)
= 𝑃(𝑥 = 3) + 𝑃(𝑥 = 4) + 𝑃(𝑥 = 5) − − − 𝑃(𝑥 = 20)
= 1 − 𝑃(𝑥 < 3)
= 1 − [𝑃(𝑥 = 0) + 𝑃(𝑥 = 1) + 𝑃(𝑥 = 2)]
= 1 − [20𝐶0 (0.1)0 (0.9)20−0 + 20𝐶1 (0.1)1 (0.9)20−1 + 20𝐶2 (0.1)2 (0.9)20−2 ]
= 0.323
Thus the number of defectives in 1000 samples is 1000 𝑋 0.323 = 323

Problem-3: The probability that a man aged 60 will live to be 70 is 0.65. What is the probability
that out of ten men now aged 60, (i) at least 7 will live to be 70. (ii) exactly 9 will live up to 70.
(iii) at most 9 will live up to 70.
Solution:
We have 𝑃(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥
Let 𝑥 be the number of persons aged 60 years living upto 70 years
By data 𝑝 = 0.65, 𝑞 = 1 − 𝑝 = 1 − 0.65 = 0.35 𝑎𝑛𝑑 𝑛 = 10
∴ 𝑃(𝑥) = 10𝐶𝑥 (0.65)𝑥 (0.35)10−𝑥
We have to find 𝑃(𝑥 ≥ 7)
= 𝑃(𝑥 = 7) + 𝑃(𝑥 = 8) + 𝑃(𝑥 = 9) + 𝑃(𝑥 = 10)
= 10𝐶7 (0.65)7 (0.35)10−7 + 10𝐶8 (0.65)8 (0.35)10−8 +
10𝐶9 (0.65)9 (0.35)10−9 + 10𝐶10 (0.65)10 (0.35)10−10
𝑃(𝑥 ≥ 7) = 0.5138
Problem -4: The probability that a pen manufactured by a factory be defective is 1/10. If 12 such
pens are manufactured, what is the probability that (i) exactly 2 are defective (ii) atleast 2 are
defective (iii) none of them are defective.
Solution:
We have 𝑃(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥
Probability of defective pen is 𝑝 = 1/10 = 0.1
Probability of non-defective pen is 𝑞 = 1 − 𝑝 = 0.9 and 𝑛 = 12
∴ 𝑃(𝑥) = 12𝐶𝑥 (0.1)𝑥 (0.9)12−𝑥
i) P(exactly 2 are defective) = 𝑃(𝑥 = 2)
= 12𝐶2 (0.1)2 (0.9)12−2
= 0.2301
ii) P(atleast 2 are defective ) = 𝑃(𝑥 ≥ 2)
= 1 − 𝑃(𝑥 < 2)
= 1 − [ 𝑃(𝑥 = 0) + 𝑃(𝑥 = 1)]
= 1 − [ 12𝐶0 (0.1)0 (0.9)12−0 + 12𝐶1 (0.1)1 (0.9)12−1 ]
= 0.341
iii) P(none of them are defective) = 𝑃(𝑥 = 0)
= 12𝐶0 (0.1)0 (0.9)12−0
= 0.2824

Problem-5: The number of telephone lines busy at an instant of time is binomial variate with
probability 0.1 that a line is busy. If 10 lines are chosen at random, what is the probability that (i)
no line is busy (ii) all lines are busy (iii) atleast one line is busy (iv) atmost 2 lines are busy.
Solution:
We have 𝑃(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥
Let 𝑥 denote the number of telephone lines busy.
By data, 𝑝 = 0.1, 𝑞 = 0.9 𝑎𝑛𝑑 𝑛 = 10
∴ 𝑃(𝑥) = 10𝐶𝑥 (0.1)𝑥 (0.9)10−𝑥
i) P(no line is busy ) = 𝑃(𝑥 = 0)
= 10𝐶0 (0.1)0 (0.9)10−0
= 0.3487
ii) P(all lines are busy) = 𝑃(𝑥 = 10)
= 10𝐶10 (0.1)10 (0.9)10−10
= (0.1)10
iii) P(atleast one line is busy) = 𝑃(𝑥 ≥ 1)
= 𝑃(𝑥 = 1) + 𝑃(𝑥 = 2) + 𝑃(𝑥 = 3) … … … 𝑃(𝑥 = 10)
= 1 − 𝑃(𝑥 < 1)
= 1 − 𝑃(𝑥 = 0)
= 1 − 10𝐶0 (0.1)0 (0.9)10−0
= 0.6513
iv) P(atmost 2 lines are busy) = 𝑃(𝑥 ≤ 2)
= 𝑃(𝑥 = 0) + 𝑃(𝑥 = 1) + 𝑃(𝑥 = 2)
= 10𝐶0 (0.1)0 (0.9)10−0 + 10𝐶1 (0.1)1 (0.9)10−1 + 10𝐶2 (0.1)2 (0.9)10−2
= 0.9298

Problem-6: An air line knows that 5% of the people making reservations on a certin flight will not
turn up. Consequently their policy is to sell 52 tickets for a flight that can only hold 50 people.
What is the probability that there will be a seat forevery passenger who turns up?
Solution:
We have 𝑃(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥
Let 𝑥 denote the number of passengers who will not turn up
By data, 𝑝 = 0.05, 𝑞 = 0.95 𝑎𝑛𝑑 𝑛 = 52
∴ 𝑃(𝑥) = 52𝐶𝑥 (0.05)𝑥 (0.95)52−𝑥
A seat is assured for every passenger who turns up if the number of passengers who fail to turn up
is more than or equal to 2
We have to find 𝑃(𝑥 ≥ 2)
𝑃(𝑥 ≥ 2) = 1 − 𝑃(𝑥 < 2)
 = 1 − [𝑃(𝑥 = 0) + 𝑃(𝑥 = 1)]
= 1 − [52𝐶0 (0.05)0 (0.95)52−0 + 52𝐶1 (0.05)1 (0.95)52−1 ]
= 1 − 0.2595
= 0.7405
Probability that a seat is available for every passenger is 0.7405

Problem- 7: Five dice are thrown 96 times and the number 1, 2, 3 appearing on the face of the
dice follows the frequency distribution as below.
𝑁𝑜. 𝑜𝑓 𝑑𝑖𝑐𝑒 𝑠ℎ𝑜𝑤𝑖𝑛𝑔 1,2,3 5 4 3 2 1 0
𝑓𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦 7 19 35 24 8 3

Solution:
We have 𝑃(𝑥) = 𝑛𝐶 𝑥 𝑝 𝑥 𝑞 𝑛−𝑥
𝑃 =Probability of getting 1 𝑜𝑟 3 𝑜𝑟 5 = 3/6 = 1/2 ∴ 𝑞 = 1/2
Here, Let 𝑥 denote the number of items an odd number turning out.
Binomial Distribution Probability function is
𝑃(𝑥) = 𝑛𝐶 𝑥 𝑝 𝑥 𝑞 𝑛−𝑥 𝑤ℎ𝑒𝑟𝑒 𝑛 = 5
1 𝑥 1 5−𝑥 1
𝑃(𝑥) = 5𝐶 𝑥 (2) (2) = 5𝐶 𝑥 is the Binomial probability distribution function.
25

Since 5 dice were thrown 96 times, expected frequencies are obtained from
𝑓(𝑥) = 96 𝑃(𝑥) where 𝑥 = 0, 1, 2, 3, 4, 5
1 96
∴ 𝑓(𝑥) = 96 5𝐶 = 5𝑐 𝑥
25 𝑥 32

∴ 𝑓(𝑥) = (3) 5𝐶 𝑥 𝑝𝑢𝑡 𝑥 = 0, 1, 2, 3, 4, 5

Hence, 𝑓(0) = (3) 5𝐶 0 = 3
𝑓(1) = (3) 5𝐶 1 = 3 × 5 = 15 𝑓(2) = (3) 5𝐶 2 = 3 × 10 = 30
𝑓(3) = (3) 5𝐶 3 = 3 × 10 = 30 𝑓(4) = (3) 5𝐶 4 = 3 × 5 = 15
𝑓(5) = (3) 5𝐶 4 = 3 × 1 = 3
The Expected (theoretical) frequencies are 3, 15, 30, 30, 15, 3
Problem-8: Four coins are tossed 100 times and following results were obtained. Fit a binomial
distribution for the data
𝑁𝑜. 𝑜𝑓 ℎ𝑒𝑎𝑑𝑠 0 1 2 3 4
𝑓𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦 5 29 36 25 5

Solution:
We have 𝑃(𝑥) = 𝑛𝐶 𝑥 𝑝 𝑥 𝑞 𝑛−𝑥
Let 𝑥 denote the number of heads and 𝑓 the corresponding frequency.
Since, the data is in the form of a frequency distribution we shall first calculate the mean,
5+29+36+25+5 196
Mean (𝜇) = = 100 = 1.96 𝑎𝑛𝑑 𝑛 = 4
100

But, In Binomial Distribution Mean (𝜇) = 𝑛𝑝

Hence 4𝑝 = 1.96
1.96
𝑝= = 0.49,
4
𝑞 = 1 − 𝑝 = 0.51
Binomial Distribution Probability function is
𝑃(𝑥) = 𝑛𝐶 𝑥 𝑝 𝑥 𝑞 𝑛−𝑥 𝑤ℎ𝑒𝑟𝑒 𝑛 = 4
𝑃(𝑥) = 4𝐶 𝑥 (0.49)𝑥 (0.51)4−𝑥

Since Four coins are tossed 100 times, expected (theoretical) frequencies are obtained by
𝑓(𝑥) = 100 𝑝(𝑥) = (100 ) 4𝐶 𝑥 (0.49)𝑥 (0.51)4−𝑥
𝑝𝑢𝑡 𝑥 = 0, 1, 2, 3, 4
𝑓(0) = (100 ) 4𝐶 0 (0.49)0 (0.51)4−0 = 6.765 ≈ 7
𝑓(1) = (100 ) 4𝐶 1 (0.49)1 (0.51)4−1 = 25.999 ≈ 26
𝑓(2) = (100 ) 4𝐶 2 (0.49)2 (0.51)4−2 = 37.47 ≈ 37
𝑓(3) = (100 ) 4𝐶 3 (0.49)3 (0.51)4−3 = 24.00.4 ≈ 24
𝑓(4) = (100 ) 4𝐶 4 (0.49)4 (0.51)4−4 = 5.765 ≈ 6
The Expected (theoretical) frequencies 𝑎𝑟𝑒 7, 26, 37, 24, 6
Problem-1: A certain screw making machine produces on an average two defectives out of 100
and packs them in boxes of 500. Find the probability that the box contains (i) Three defectives (ii)
At least one defective (iii) Between two and four defectives (iv) 15 defective screws.
Solution :
𝑚𝑥 𝑒 −𝑚
We have Poisson distribution of the random variable is 𝑃(𝑥) = 𝑥!

By data, Mean (𝜇) = 𝑚 = 2

2𝑥 𝑒 −2
∴ 𝑃(𝑥) = Here 𝑒 −2 = 0.1353
𝑥!
2𝑥
∴ 𝑃(𝑥) = 0.1353 𝑥!

i) P(Three defectives) = 𝑃(𝑥 = 3)

22
= 0.1353 2!

= 0.2706
ii) P(At least one defective) = 𝑃(𝑥 ≥ 1)
= 1 − 𝑃(𝑥 < 1)
= 1 − [𝑃(𝑥 = 0)]
20
= 1 − [0.1353 ]
0!

= 0.8647
iii) P(Between two and four defectives) = 𝑃(𝑥 = 3)
22
= 0.1353 2!

= 0.2706
iv) P(15 defective screws) = 𝑃(𝑥 = 15)
215
= 0.1353 15 !

Problem-2: A car hire firm has 2 cars, which it hires out day by day. The demand for a car on each
day is distributed as a Poisson distribution with mean 1.5. Calculate the probability that on a certain
day (i) neither car is used and (ii) some demand is refused.
Solution :
 𝑚𝑥 𝑒 −𝑚
We have Poisson distribution of the random variable is 𝑃(𝑥) = 𝑥!

By data, Mean (𝜇) = 𝑚 = 1.5

1.5𝑥 𝑒 −1.5
∴ 𝑃(𝑥) = Here 𝑒 −1.5 = 0.2231
𝑥!
1.5𝑥
∴ 𝑃(𝑥) = 0.2231 𝑥!

i) P( neither car is used) = 𝑃(𝑥 = 0)

1.50
= 0.2231 0!

= 0.2231
ii) P(some demand is refused) = 𝑃(𝑥 ≥ 2)
= 1 − 𝑃(𝑥 < 2)
= 1 − [𝑃(𝑥 = 0) + 𝑃(𝑥 = 1)]
1.50 1.51
= 1 − [0.2231 + 0.2231 ]
0! 1!

= 0.44225

Problem-3: In a certain factory turning out blades, there is a small chance of 0.002 for any blade
to be defective. The blades are supplied in packets of 10. Using Poisson distribution find the
approximate number of packets containing (i) no defective blade (ii) one defective blade in a
consignment of 10, 000 packets.
Solution :
𝑚𝑥 𝑒 −𝑚
We have Poisson distribution of the random variable is 𝑃(𝑥) = 𝑥!

By data, 𝑝 =Probability of defective blade = 1/500 = 0.002, n=10

In packets of 10, mean number of defective blade is 𝑚 = 𝑛𝑝
𝑚 = 𝑛𝑝 = 10 𝑋 0.002 = 0.02
0.02𝑥 𝑒 −0.02
∴ 𝑃(𝑥) = Here 𝑒 −0.02 = 0.9802
𝑥!
0.02𝑥
∴ 𝑃(𝑥) = 0.9802 𝑥!

Let 𝑓(𝑥) = 10,000 𝑃(𝑥)

0.02𝑥
𝑓(𝑥) = 10,000 (0.9802 ) 𝑥!
 0.02𝑥
𝑓(𝑥) = 9802 𝑥!
0.020
i) P(no defective blade) = 9802 = 9802
0!
0.021
ii) P(one defective blade) = 9802 = 196
1!

Problem-4: The number of accidents in a year to taxi drivers in a city follows a Poisson distribution
with mean 3 out of 1000 taxi drivers find approximately the number of drivers with (i) no accident
in a year (ii) more than 3 accidents in a year.
Solution :
𝑚𝑥 𝑒 −𝑚
We have Poisson distribution of the random variable is 𝑃(𝑥) = 𝑥!

By Data, Mean (𝜇) = 𝑚 = 3

3𝑥 𝑒 −3
∴ 𝑃(𝑥) = Here 𝑒 −3 = 0.05
𝑥!
3𝑥
∴ 𝑃(𝑥) = 0.05 𝑥!
30
i) Number of drivers with no accident in a year = 𝑃(𝑥 = 0) = 0.05 = 0.05
0!

Number of drivers out of 1000 with no accident in a year = 1000 𝑋 0.05 = 50

ii) P(more than 3 accidents in a year) = 𝑃(𝑥 > 3)

= 1 − 𝑃(𝑥 ≤ 3)
= 1 − [ 𝑃(𝑥 = 0) + 𝑃(𝑥 = 1) + 𝑃(𝑥 = 2) + 𝑃(𝑥 = 3)
30 31 32 33
= 1 − [ 0.05 + 0.05 + 0.05 + 0.05
0! 1! 2! 3!

= 0.35
Number of drivers out of 1000 with more than 3 accidents in a year = 1000 𝑋 0.35 = 350

Problem-5: 2% of the fuses manufactured by a firm are found to be defective. Find the
probability that a box containing 200 fuses contains (i) no defective fuses (ii) 3 or more
defective fuses.

Solution :
𝑚𝑥 𝑒 −𝑚
We have Poisson distribution of the random variable is 𝑃(𝑥) = 𝑥!
 By Data, 𝑝 = Probability of a defective fuses = 2/100 =0.02
Mean (𝜇) number of defective fuses= 𝑚 = 𝑛𝑝 = 0.02 𝑋 200 = 4
4𝑥 𝑒 −4
∴ 𝑃(𝑥) = Here 𝑒 −4 = 0.0183
𝑥!
4𝑥
∴ 𝑃(𝑥) = 0.0183 𝑥!

i) P(no defective fuses ) = 𝑃(𝑥 = 0)

40
= 0.0183 = 0.0183
0!

ii) P(3 or more defective fuses.) = 𝑃(𝑥 ≥ 3)

= 1 − 𝑃(𝑥 < 3)
= 1 − [𝑃(𝑥 = 0) + 𝑃(𝑥 = 1) + 𝑃(𝑥 = 2)]
40 41 42
= 1 − [0.0183 + 0.0183 + 0.0183 ]
0! 1! 2!
= 0.7621

Problem-6: Fit a Poisson distribution for the following data,

𝑋 0 1 2 3 4
𝐹 122 60 15 2 1
𝑚𝑥 𝑒 −𝑚
Solution: We have Poisson Distribution 𝑃(𝑥) = 𝑥 !
∑ 𝑓𝑥 0(122)+1(60)+2(15)+3(2)+4(1)
Mean in Poisson Distribution (𝜇) = 𝑚 = ∑𝑓
= = 0.5
122+60+15+2+1

(0.5)𝑥 𝑒 −(0.5)
∴ Poisson Distribution 𝑃(𝑥) = 𝑥 !

Expected frequencies 𝑓(𝑥) = 200 𝑃(𝑥)

(0.5)𝑥 𝑒 −(0.5)
𝑓(𝑥) = 200 𝐵𝑢𝑡 𝑒 −(0.5) = 0.6065
𝑥 !

(0.5)𝑥
𝑓(𝑥) = (121.3)
𝑥 !
𝑃𝑢𝑡 𝑥 = 0, 1, 2, 3, 4
(0.5)0 (0.5)1
𝑓(0) = (121.3) = 121 𝑓(1) = (121.3) ≈ 61
0! 1!
(0.5)2 (0.5)3
𝑓(2) = (121.3) ≈ 15 𝑓(3) = (121.3) ≈3
2! 3!

(0.5)4
𝑓(4) = (121.3) ≈0
4!
The Expected (theoretical) frequencies 𝑎𝑟𝑒 121, 61, 15, 3, 0
Continuous Probability Distributions:
We have already defined that a random variable which takes non-countable infinite number of
values is called a continuous random variable.

Definition: If for every x belonging to the range of a continuous random variable X we assign
a real number 𝑓(𝑥) satisfying the conditions
𝑖) 𝑓(𝑥) ≥ 0
∞
𝑖𝑖) ∫−∞ 𝑓(𝑥)𝑑𝑥 = 1
then 𝑓(𝑥) is called a continuous probability function or probability density function (p.df)

If (𝑎, 𝑏) is a subinterval of the range space x then probability that 𝑥 lies in (𝑎, 𝑏)
𝑏
i.e) 𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫𝑎 𝑓(𝑥)𝑑𝑥

Cumulative Distribution Function:

If 𝑋 is a continuous random variable with probability density function 𝑓(𝑥) then
𝑥
𝐹(𝑥) = 𝑃(𝑋 ≤ 𝑥) = ∫−∞ 𝑓(𝑥) 𝑑𝑥 is called the cumulative density function (c.d.f) of 𝑋

Not:- If 𝑟 any real number then

∞
𝑃(𝑋 ≥ 𝑟) = ∫𝑟 𝑓(𝑥) 𝑑𝑥

𝑃(𝑋 < 𝑟) = 1 − 𝑃(𝑋 ≥ 𝑟)

∞
𝑖. 𝑒. 𝑃(𝑋 < 𝑟) = 1 − ∫𝑟 𝑓(𝑥) 𝑑𝑥

Mean and Variance:

If 𝑋 is a continuous random variable with probability density function 𝑓(𝑥) 𝑤ℎ𝑒𝑟𝑒 − ∞ < 𝑥 <
∞
∞
Then Mean (𝜇) or Expectation 𝐸(𝑋) = ∫−∞ 𝑥 𝑓(𝑥)𝑑𝑥
∞
Variance (𝜎 2 ) = ∫−∞(𝑥 − 𝜇)2 𝑓(𝑥)𝑑𝑥

1. Exponential Distribution:
A continuous probability distribution having the probability density function 𝑓(𝑥) given by
𝛼 𝑒 −𝛼𝑥 𝑓𝑜𝑟 𝑥 > 0
𝑓(𝑥) = { is known as the exponential distribution
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒, 𝑤ℎ𝑒𝑟𝑒 𝛼 > 0
Here 𝑖) 𝑓(𝑥) ≥ 0
∞ ∞ 𝑒 −𝛼𝑥 ∞
𝑖𝑖) ∫−∞ 𝑓(𝑥) 𝑑𝑥 = ∫0 𝛼 𝑒 −𝛼𝑥 𝑑𝑥 = 𝛼 [ ] = −(0 − 1) = 1
−𝛼 0
 Mean and Standard Deviation of the Exponential Distribution:
1
Then Mean (𝜇) or Expectation 𝐸(𝑋) = 𝛼
1
Variance (𝜎 2 ) = 𝜎2
1
Standard Deviation ((𝜎) = √𝑉 = 𝛼

𝑘 𝑥3, 0<𝑥<1
Example-1: Given 𝑓(𝑥) = { , Find (i) k so that 𝑓(𝑥) is the
0, 𝑂𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
1 3 1 4
probability density function. (ii) 𝑃 (4 < 𝑋 < 4) (iii) 𝑃 (𝑋 < 2) (iv) 𝑃 (𝑋 > 5)
∞
Solution : W.K.T 𝑓(𝑥) ≥ 0, 𝑖𝑓 𝑘 > 0. Also we must have ∫−∞ 𝑓(𝑥) 𝑑𝑥 = 1
1
∞ 1 𝑥4 𝑘
∫−∞ 𝑓(𝑥) 𝑑𝑥 = ∫0 𝑘 𝑥 3 𝑑𝑥 = 𝑘 [ 4 ] = 4 (1 − 0) = 1 Then 𝑘 = 4
0
1 3
ii) 𝑃 (4 < 𝑋 < 4) =?
𝑏
We have 𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫𝑎 𝑓(𝑥)𝑑𝑥
3 3
1 3 4 3 𝑥4 4
𝑃 (4 < 𝑥 < 4) = ∫ 4𝑥 𝑑𝑥 = 4 [ 4 ]1 1
4 4

3/4 34 1 26
= [𝑥 4 ]1/4 = [44 − 44 ] = 256
1
iii) 𝑃 (𝑋 < 2) =?
𝑏
We have 𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫𝑎 𝑓(𝑥)𝑑𝑥
1
1
1 3 𝑥4 2
𝑃 (𝑋 < 2) = ∫0 4𝑥 𝑑𝑥 = 4 [ 4 ]
2
0
1
1 1
= [𝑥 4 ]20 = [24 − 0] = 16
4
iv) 𝑃 (𝑋 > 5) =?
𝑏
We have 𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫𝑎 𝑓(𝑥)𝑑𝑥
1
4 1 𝑥4
𝑃 (𝑋 > 5) = ∫4 4𝑥 3 𝑑𝑥 = 4 [ 4 ]4
5 5

4 4 369
= [𝑥 4 ]14 = [1 − [5] ] =
5
625
 𝑘 𝑥 𝑒 −𝑥 , 0<𝑥<1
2) Find 𝐾 such that 𝑓(𝑥) = { is a P.d.f. Find mean
0, 𝑂𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
∞
Solution: W.K.T 𝑓(𝑥) ≥ 0, 𝑖𝑓 𝑘 > 0. Also we must have ∫−∞ 𝑓(𝑥) 𝑑𝑥 = 1
∞ 1
∫−∞ 𝑓(𝑥) 𝑑𝑥 = ∫0 𝑘 𝑥 𝑒 −𝑥 𝑑𝑥 = 1
Applying Bernoulli’s rule, we have
∫ 𝑢𝑣 𝑑𝑥 = 𝑢𝑣1 − 𝑢𝐼 𝑣2 + 𝑢𝐼𝐼 𝑣3 − 𝑢𝐼𝐼𝐼 𝑣4 + − − − −
𝐾[𝑥 (−𝑒 −𝑥 ) − (1)(𝑒 −𝑥 )]10 = 1
𝐾[(−𝑒 −1 − 0) − (𝑒 −1 − 𝑒 0 )] = 1
1 1
𝐾 [− − + 1] =1
𝑒 𝑒
2 𝑒
𝐾 [1 − 𝑒] = 1 ∴ 𝑘 = 𝑒−2
∞
Mean (𝜇) or Expectation 𝐸(𝑋) = ∫−∞ 𝑥 𝑓(𝑥)𝑑𝑥
1
= ∫0 𝑥 𝑘 𝑥 𝑒 −𝑥 𝑑𝑥
1 𝑒
= ∫0 𝑥 𝑥 𝑒 −𝑥 𝑑𝑥
𝑒−2
𝑒 1
= ∫ 𝑥 2 𝑒 −𝑥 𝑑𝑥
𝑒−2 0

Applying Bernoulli’s rule, we have

∫ 𝑢𝑣 𝑑𝑥 = 𝑢𝑣1 − 𝑢𝐼 𝑣2 + 𝑢𝐼𝐼 𝑣3 − 𝑢𝐼𝐼𝐼 𝑣4 + − − − −
𝑒
= [𝑥 2 (−𝑒 −𝑥 ) − (2𝑥)(𝑒 −𝑥 ) + 2(−𝑒 −𝑥 )]10
𝑒−2
𝑒
= [(−𝑒 −1 − 0) − (2𝑒 −1 − 0) − 2(𝑒 −1 − 𝑒 0 )]
𝑒−2
𝑒 1 2 2
= [− 𝑒 − 𝑒 − 𝑒 + 2]
𝑒−2
𝑒 5
= [2 − 𝑒]
𝑒−2

𝑘 𝑥2, 0<𝑥<3
3) Find the constant k such that 𝑓(𝑥) = { is a p.d.f. Also Compute
0, 𝑂𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
𝑖) 𝑃(1 < 𝑥 < 2) 𝑖𝑖) 𝑃(𝑥 ≤ 1) 𝑖𝑖𝑖) 𝑃(𝑥 > 1) 𝑖𝑣) 𝑀𝑒𝑎𝑛 𝑣) 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒
∞
Solution: W.K.T 𝑓(𝑥) ≥ 0, 𝑖𝑓 𝑘 > 0. Also we must have ∫−∞ 𝑓(𝑥) 𝑑𝑥 = 1
3
∞ 3 𝑥3 𝑘 1
∫−∞ 𝑓(𝑥) 𝑑𝑥 = ∫0 𝑘 𝑥 2 𝑑𝑥 = 𝑘 [ 3 ] = 3 (27 − 0) = 1 ∴ 𝑘=9
0
i) 𝑃(1 < 𝑋 < 2) =?
𝑏
We have 𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫𝑎 𝑓(𝑥)𝑑𝑥
2
21 1 𝑥3
𝑃(1 < 𝑥 < 2) = ∫1 9 𝑥 2 𝑑𝑥 = 9 [ 3 ]
1
1 7
𝑃(1 < 𝑥 < 2) = 27 [8 − 1] = 27

ii) 𝑃(𝑋 ≤ 1) =?
𝑏
We have 𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫𝑎 𝑓(𝑥)𝑑𝑥
1
11 1 𝑥3
𝑃(𝑋 ≤ 1) = ∫0 9 𝑥 2 𝑑𝑥 = 9 [ 3 ]
0
1 1
𝑃(𝑋 ≤ 1) = 27 [1 − 0] = 27
𝑏
iii) 𝑃(𝑋 > 1) =? We have 𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫𝑎 𝑓(𝑥)𝑑𝑥
3
31 1 𝑥3
𝑃(𝑋 > 1) = ∫1 9 𝑥 2 𝑑𝑥 = 9 [ 3 ]
1
1 26
𝑃(𝑋 > 1) = 27 [27 − 1] = 27
∞
iv) Mean (𝜇) or Expectation 𝐸(𝑋) = ∫−∞ 𝑥 𝑓(𝑥)𝑑𝑥
3
= ∫0 𝑥 𝑘 𝑥 2 𝑑𝑥
3 1
= ∫0 𝑥 𝑥 2 𝑑𝑥
9
1 3
= 9 ∫0 𝑥 3 𝑑𝑥
3
1 𝑥4 1 81 9
= [
9 4 0
] = 36 [81 − 0] = 36
=4
∞
v) Variance 𝑉 = ∫−∞ 𝑥 2 𝑓(𝑥)𝑑𝑥 − (𝜇)2

3 1 9 2
𝑉 = ∫0 𝑥 2 𝑥 2 𝑑𝑥 − (4 )
9

3 1 9 2
𝑉 = ∫0 𝑥 4 𝑑𝑥 − (4 )
9
3
1 𝑥5 81 243 81 27
𝑉= [ ] − = − =
9 5 0 36 45 36 80
 𝑥
+ 𝑐, 0 < 𝑥 < 3
4) Find the value of C such that 𝑓(𝑥) = {6 is a p.d.f Also find 𝑃(1 ≤ 𝑋 ≤ 2)
0, 𝑂𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
∞
Solution: W.K.T 𝑓(𝑥) ≥ 0, 𝑖𝑓 𝑘 > 0. Also we must have ∫−∞ 𝑓(𝑥) 𝑑𝑥 = 1
3
∞ 3𝑥 𝑥2
∫−∞ 𝑓(𝑥) 𝑑𝑥 = ∫0 6
+ 𝑐 𝑑𝑥 = [12 + 𝑐𝑥]
0
1
= 12 (9 − 0) + (3𝑐 − 0)
3
→ 4 + 3𝑐 = 1
3
→ 3𝑐 = 1 − 4
1 1
→ 3𝑐 = 4 ∴ 𝐶 = 12

i) 𝑃(1 ≤ 𝑋 ≤ 2) =?
𝑏
We have 𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫𝑎 𝑓(𝑥)𝑑𝑥
2 𝑥 2 𝑥 1
𝑃(1 ≤ 𝑋 ≤ 2) = ∫1 (6 + 𝑐) 𝑑𝑥 == ∫1 (6 + 12) 𝑑𝑥
2
𝑥2 𝑥 1 4
𝑃(1 ≤ 𝑋 ≤ 2) = [12 + 12] = 12 [4 − 1 + 2 − 1] = 12
1

𝑘 𝑥2 , −3<𝑥 <3
5. A random variable X has the following density function 𝑓(𝑥) = {
0, 𝑂𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
Evaluate K, 𝑃(1 ≤ 𝑋 ≤ 2), 𝑃(𝑋 ≤ 2), 𝑃(𝑋 > 1)

Exponential Distribution:

A continuous probability distribution having the probability density function 𝑓(𝑥) given by
𝛼 𝑒 −𝛼𝑥 𝑓𝑜𝑟 𝑥 > 0
𝑓(𝑥) = { is known as the exponential distribution
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒, 𝑤ℎ𝑒𝑟𝑒 𝛼 > 0
Here 𝑖) 𝑓(𝑥) ≥ 0
∞ ∞ 𝑒 −𝛼𝑥 ∞
𝑖𝑖) ∫−∞ 𝑓(𝑥) 𝑑𝑥 = ∫0 𝛼 𝑒 −𝛼𝑥 𝑑𝑥 = 𝛼 [ ] = −(0 − 1) = 1
−𝛼 0

Mean and Standard Deviation of the Exponential Distribution:

1
Then Mean (𝜇) or Expectation 𝐸(𝑋) = 𝛼
1
Variance (𝜎 2 ) = 𝜎2
1
Standard Deviation ((𝜎) = √𝑉 = 𝛼
1. In a certain town the duration of a shower is exponentially distributed with mean 5 minutes.
What is the probability that a shower will lost for (i) 10 minutes or more (ii) less than 10
minutes (iii) between 10 minutes and 12 minutes.

𝛼 𝑒 −𝛼𝑥 𝑓𝑜𝑟 𝑥 > 0

Solution: We have Exponential Distribution 𝑓(𝑥) = {
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒,
1
In Exponential Distribution, Mean (𝜇) = 𝛼
1 1
By data, Mean(𝜇) = 5 = 𝛼 ∴ 𝛼=5
𝑥
1
∴ 𝑓(𝑥) = 𝑒 −5 𝑤ℎ𝑒𝑛 𝑥 > 0
5

𝑖) Probability that a shower will lost for 10 minutes or more = P(x ≥ 10)
∞ 1 𝑥
P(x ≥ 10) = ∫10 𝑒 −5 𝑑𝑥
5
−𝑥 ∞
1 𝑒5
= [ 1 ]
5 (− )
5 10
−10
P(x ≥ 10) = − { 𝑒 −∞ − 𝑒 5 } = 𝑒 −2 = 0.1353

𝑖𝑖) Probability that a shower will lost for less than 10 minutes= P(x ≤ 10)
𝑥
10 1
P(x ≤ 10) = ∫0 𝑒 −5 𝑑𝑥
5
−𝑥 10
1 𝑒5
= [ 1 ]
5 (− )
5 0
−10
P(x ≤ 10) = − { 𝑒 5 − 𝑒 0 } = − 𝑒 −2 + 1 = 0.8647

𝑖𝑖𝑖) Probability that a shower will lost for between 10 minutes and 12 minutes= P(10 ≤ x ≤ 12)
𝑥
12 1
P(10 ≤ x ≤ 12) = ∫10 𝑒 −5 𝑑𝑥
5
−𝑥 12
1 𝑒5
= [ 1 ]
5 (− )
5 10
−12 −10 −12
P(10 ≤ x ≤ 12) = − { 𝑒 5 −𝑒 5 } = −𝑒 5 + 𝑒 −2 = 0.0446
2. The length of telephone conversation in a booth has been an exponential distribution and found
on an average to be 5 minutes. Find the probability that a random call made from this booth (i)
less than 5 minutes (ii) between 5 and 10 minutes.
𝛼 𝑒 −𝛼𝑥 𝑓𝑜𝑟 𝑥 > 0
Solution: We have Exponential Distribution 𝑓(𝑥) = {
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒,
1
In Exponential Distribution, Mean (𝜇) = 𝛼
1 1
By data, Mean(𝜇) = 5 = ∴ 𝛼=
𝛼 5
𝑥
1 −
∴ 𝑓(𝑥) = 𝑒 5 𝑤ℎ𝑒𝑛 𝑥 > 0 is the p.d.f
5

𝑖) Probability that a random call made from this booth less than 5 minutes= P(x < 5)
𝑥
5 1
P(x < 5) = ∫0 𝑒 −5 𝑑𝑥
5
−𝑥 5
1 𝑒5
= [ 1 ]
5 (− )
5 0
−5
P(x < 5) = − { 𝑒 5 − 𝑒 0 } = − 𝑒 −1 + 1 = 0.6321

𝑖𝑖) Probability that a random call made in this booth between 5 and 10 minutes = P(5 < x < 10)
𝑥
10 1
P(5 < x < 10) = ∫5 𝑒 −5 𝑑𝑥
5
−𝑥 10
1 𝑒5
= [ 1 ]
5 (− )
5 5
−10 −5
P(5 ≤ x ≤ 10) = − { 𝑒 5 − 𝑒 5 } = −𝑒 −2 + 𝑒 −1 = 0.2325

3. The duration of a telephone conversation has been found to have an exponential distribution
with mean 3 minutes. Find the probability that the conversation may lost (i) more than 1 minutes
(ii) less than 3 minutes (iii) between 3 and 5 minutes.
4. The sales per day in a shop is exponentially distributed with the average sale amounting to Rs
100 and net profit is 8%. Find the probability that the net profit exceeds Rs 30 on a day.

Solution: Let x be the random variable of the sale in the shop.

𝛼 𝑒 −𝛼𝑥 𝑓𝑜𝑟 𝑥 > 0
Since x is an exponential variate the p.d.f 𝑓(𝑥) = {
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒,
1
In Exponential Distribution, Mean (𝜇) = 𝛼
1 1
By data, Mean(𝜇) = 100 = ∴ 𝛼= = 0.01
𝛼 100

∴ 𝑓(𝑥) = 0.01 𝑒 −0.01 𝑥 𝑤ℎ𝑒𝑛 𝑥 > 0 is the p.d.f

Let A be the amount for which profit is 8%
8
𝑖. 𝑒 𝐴 = 30 ∴ 𝐴 = 375
100

Probability that the net profit exceeds Rs 30 = 1 − 𝑃𝑟𝑜𝑏(𝑃𝑟𝑜𝑓𝑖𝑡 ≤ 𝑅𝑠. 30)

= 1 − 𝑃𝑟𝑜𝑏(𝑃𝑟𝑜𝑓𝑖𝑡 ≤ 𝑅𝑠. 375)
375
= 1 − ∫0 0.01 𝑒 −0.01 𝑥 𝑑𝑥
375
𝑒 −0.01 𝑥
= 1 − 0.01 [ ]
−0.01 0

= 1 + 𝑒 −0.01 (375) − 𝑒 0 = 𝑒 −3.75

Probability that the net profit exceeds Rs 30 on a single day is 𝑒 −3.75

5. The sales per day in a shop is exponentially distributed with the average sale amounting to Rs
100 and net profit is 8%. Find the probability that the net profit exceeds Rs 30 on two
consecutive days.
Solution: Let x be the random variable of the sale in the shop.
𝛼 𝑒 −𝛼𝑥 𝑓𝑜𝑟 𝑥 > 0
Since x is an exponential variate the p.d.f 𝑓(𝑥) = {
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒,
1
In Exponential Distribution, Mean (𝜇) = 𝛼
1 1
By data, Mean(𝜇) = 100 = 𝛼 ∴ 𝛼 = 100 = 0.01

∴ 𝑓(𝑥) = 0.01 𝑒 −0.01 𝑥 𝑤ℎ𝑒𝑛 𝑥 > 0 is the p.d.f

Let A be the amount for which profit is 8%
 8
𝑖. 𝑒 𝐴 = 30 ∴ 𝐴 = 375
100

Probability that the net profit exceeds Rs 30 = 1 − 𝑃𝑟𝑜𝑏(𝑃𝑟𝑜𝑓𝑖𝑡 ≤ 𝑅𝑠. 30)

= 1 − 𝑃𝑟𝑜𝑏(𝑃𝑟𝑜𝑓𝑖𝑡 ≤ 𝑅𝑠. 375)
375
= 1 − ∫0 0.01 𝑒 −0.01 𝑥 𝑑𝑥
375
𝑒 −0.01 𝑥
= 1 − 0.01 [ ]
−0.01 0

= 1 + 𝑒 −0.01 (375) − 𝑒 0 = 𝑒 −3.75

Probability that the net profit exceeds Rs 30 on a single day is 𝑒 −3.75
Thus the probability that it repeats on the following day is 𝑒 −3.75 . 𝑒 −7.5 = 𝑒 −3.75 = 0.00055

2. Normal Distribution:
The continuous probability distribution having the probability density function 𝑓(𝑥) given by
−(𝑥−𝜇)2
1
𝑓(𝑥) = 𝜎√2𝜋 𝑒 2𝜎2 where −∞ < 𝑥 < ∞, −∞ < 𝜇 < ∞ 𝑎𝑛𝑑 𝜎 > 0 is known as the
∞
normal distribution. Here 𝑖) 𝑓(𝑥) ≥ 0 and 𝑖𝑖) ∫−∞ 𝑓(𝑥) 𝑑𝑥 = 1 , Here 𝑓(𝑥) represents
Probability density function.

Note: Normal distribution can be derived as a limiting case of the binomial distribution when 𝑛
1
is large, neither 𝑝 𝑛𝑜𝑟 𝑞 is very small. We can derive 𝑓(𝑥) 𝑎𝑠 𝑛 → ∞ 𝑎𝑛𝑑 𝑝 = 2 = 𝑞.

Mean and Standard Deviation of the Normal Distribution:

Then Mean (𝜇) or Expectation 𝐸(𝑋) = 𝜇
Variance (𝜎 2 ) = 𝜎2
Standard Deviation ((𝜎) = √𝑉 = 𝜎
Note: The graph of the probability function f(x) is a bell shaped curve symmetrical about the line
𝑥 = 𝜇 and is called the normal probability curve. Shape of the curve is as follows.

The line 𝑥 = 𝜇 divides the total area under the curve which is equal to 1 into two equal parts.
The area to the right as well as to the left of the line 𝑥 = 𝜇 is 0.5.
Standard Normal Distribution:
𝑏
We have 𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫𝑎 𝑓(𝑥) 𝑑𝑥
In the case of normal distribution, we have,
−(𝑥−𝜇)2
1 𝑏
𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫ 𝑒 2𝜎2 𝑑𝑥 − − − − − − − (1)
𝜎√2𝜋 𝑎
𝑥−𝜇
Putting 𝑧 = or 𝑥 = 𝜇 + 𝜎𝑧 we have 𝑑𝑥 = 𝜎 𝑑𝑧
𝜎
𝑎−𝜇 𝑏−𝜇
Let 𝑧1 = and 𝑧2 = be the values of z corresponding to 𝑥 = 𝑎 𝑎𝑛𝑑 𝑥 = 𝑏. The
𝜎 𝜎

integral in (1) assumes the following form

−𝑧2
1 𝑧2
𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = ∫ 𝑒 2 𝑑𝑧
√2𝜋 𝑧1
−𝑧2
1 𝑧2
𝑃(𝑎 ≤ 𝑥 ≤ 𝑏) = 𝑃(𝑧1 ≤ 𝑥 ≤ 𝑧2 ) = ∫𝑧 𝑒 2 𝑑𝑧
√2𝜋 1

−𝑧2
1
Standard normal probability density function is 𝐹(𝑧) = 𝑒 2 , it may be observed that
√2𝜋

this is same as the p.d.f of the normal distribution with 𝜇 = 0 𝑎𝑛𝑑 𝜎 = 1.

Thus we can say that the normal probability density function with 𝜇 = 0 𝑎𝑛𝑑 𝜎 = 1 is the
standard normal density function.

𝑥−𝜇
𝑧= is called the standard normal variate (S.N.V) and 𝐹(𝑧) is called the standard
𝜎

normal curve which is symmetrical about the line 𝑧 = 0. The curve is as follows
 Some important results:
∞
𝑖) 𝑃(−∞ ≤ 𝑧 ≤ ∞) = ∫ ∅(𝑧)𝑑𝑧 = 1
−∞
0
𝑖𝑖) 𝑃(−∞ ≤ 𝑧 ≤ 0) = ∫ ∅(𝑧)𝑑𝑧 = 0.5
−∞
∞
𝑖𝑖𝑖) 𝑃(0 ≤ 𝑧 ≤ ∞) = ∫ ∅(𝑧)𝑑𝑧 = 0.5
0
𝑖𝑣) 𝑃(𝑧 < 𝑧1 ) = 0.5 + ∅(𝑧1 )
𝑣) 𝑃(𝑧 > 𝑧1 ) = 0.5 − ∅(𝑧1 )

1. The marks of 1000 students in an examination follows a normal distribution with mean 70 and S.D
5. Find the number of students whose marks will be (i) less than 65 ii) more than 75 iii) between
65 and 75

Solution: Let x represent the marks of students. By data, 𝜇 = 70 𝑎𝑛𝑑 𝜎 = 5,

𝑥−𝜇 𝑥−70
Standard normal variate (S.N.V) 𝑧 = =
𝜎 5

i) To find 𝑃(𝑥 < 65) = ?

If 𝑥 = 65 𝑡ℎ𝑒𝑛 𝑧 = −1
Then 𝑃(𝑥 < 65) = 𝑃(𝑧 < −1) =?
𝑃(𝑧 < −1) = 𝑃(𝑧 > 1)
= 𝑃(𝑧 ≥ 0) − 𝑃(0 < 𝑧 < 1)
= 0.5 − 𝐴(1)
= 0.5 − 0.3413 = 0.1587
Number of students scoring less than 65 marks 1000 × 0.1587 = 158.7 ≈ 159.
iii) To find 𝑃(65 < 𝑥 < 75) = ?
If 𝑥 = 65 𝑡ℎ𝑒𝑛 𝑧 = −1
If 𝑥 = 75 𝑡ℎ𝑒𝑛 𝑧 = 1
Then 𝑃(65 < 𝑥 < 75) = 𝑃(−1 < 𝑧 < 1) =?
𝑃(−1 < 𝑧 < 1) = 2𝑃(0 < 𝑧 < 1)
= 2 𝑃(0 < 𝑧 < 1)
= 2 𝐴(1)
= 2 (0.3413) = 0.6826
 Number of students scoring between 65 and 75 = 1000 × 0.6826 = 682.6 ≈ 683

ii) To find 𝑃(𝑥 > 75) = ?

If 𝑥 = 75 𝑡ℎ𝑒𝑛 𝑧 = 1
Then 𝑃(𝑥 > 75) = 𝑃(𝑧 > 1) =?
𝑃(𝑧 > 1) = 𝑃(𝑧 > 1)
= 𝑃(𝑧 ≥ 0) − 𝑃(0 < 𝑧 < 1)
= 0.5 − 𝐴(1)
= 0.5 − 0.3413 = 0.1587
Number of students scoring less than 75 marks 1000 × 0.1587 = 158.7 ≈ 159

2. In a test on electric bulbs, it was found that the life time of a particular brand was distributed
normally with an average life of 2000 hours and S.D of 60 hours. If a firm purchases 2500 bulbs
find the number of bulbs that are likely to last for (i) more than 2100 hrs (ii) less than 1950 hrs
(ii) more than 1900 hrs but less than 2100 hrs Given P(0  z  1.67) = 0.4525.

Solution: Let x represent the number of bulbs. By data, 𝜇 = 2000 𝑎𝑛𝑑 𝜎 = 60,
𝑥−𝜇 𝑥−2000
Standard normal variate (S.N.V) 𝑧 = =
𝜎 60

i) To find 𝑃(𝑥 > 2100) = ? If 𝑥 = 2100 𝑡ℎ𝑒𝑛 𝑧 = 1.67

Then 𝑃(𝑥 > 2100) = 𝑃(𝑧 > 1.67) =?
𝑃(𝑧 > 1.67) = 𝑃(𝑧 > 1.67)
= 𝑃(𝑧 ≥ 0) − 𝑃(0 < 𝑧 < 1.67)
= 0.5 − 𝐴(1.67)
= 0.5 − 0.4525 = 0.0475
Number of bulbs that are likely to last for more than 2100 hrs is 2500 × 0.0475 = 118.75 ≈ 119.

ii) To find 𝑃(𝑥 < 1950) = ? If 𝑥 = 1950 𝑡ℎ𝑒𝑛 𝑧 = −0.83

Then 𝑃(𝑥 < 1950) = 𝑃(𝑧 < −0.83) =?
𝑃(𝑧 < −0.83) = 𝑃(𝑧 > 0.83)
= 𝑃(𝑧 ≥ 0) − 𝑃(0 < 𝑧 < 0.83)
= 0.5 − 𝐴(0.83)
 = 0.5 − 0.2967 = 0.2033
Number of bulbs that are likely to last for less than 1950 hrs is 2500 × 0.2033 = 508.25 ≈ 508
iii) To find 𝑃(1900 < 𝑥 < 2100) = ?
If 𝑥 = 1900 𝑡ℎ𝑒𝑛 𝑧 = −1.67
If 𝑥 = 2100 𝑡ℎ𝑒𝑛 𝑧 = 1.67
Then 𝑃(1900 < 𝑥 < 2100) = 𝑃(−1.67 < 𝑧 < 1.67) =?
𝑃(−1.67 < 𝑧 < 1.67) = 2𝑃(0 < 𝑧 < 1.67)
= 2 𝑃(0 < 𝑧 < 1.67)
= 2 𝐴(1.67)
= 2 (0.4525) = 0.905
Number of bulbs that are likely to last for more than 1900 hrs but less than 2100 hrs
is 2500 × 0.905 = 2262.5 ≈ 2263

3. An analogy signal received as a detector (measured in micro volts) may be modelled as a Gaussian
(normal) random variable with mean 200 and variance 256 at a fixed point of time. What is the
probability that the signal will exceed 240 micro volts?

Solution:
By data, 𝜇 = 200, 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒(𝑣) = 256, 𝜎 = √256 = 16,
𝑥−𝜇 𝑥−200
Standard normal variate (S.N.V) 𝑧 = =
𝜎 16

Probability that the signal will exceed 240 micro volts 𝑃(𝑥 > 240) = ?
If 𝑥 = 240 𝑡ℎ𝑒𝑛 𝑧 = 2.5
𝑃(𝑥 > 240) = 𝑃(𝑧 > 2.5)
= 𝑃(𝑧 ≥ 0) − 𝑃(0 < 𝑧 < 2.5)
= 0.5 − 𝐴(2.5)
= 0.5 − 𝐴(2.5)

4. 200 students appeared in an examination. Distribution of marks is assumed to be normal with mean
 = 30 and S.D.  = 6.25. How many students are expected to get marks (i) between 20 and 40 (ii)
less than 35.
5. In a normal distribution 31% of the items are under 45 and 8% of the items are over 64. Find the
mean and S.D. of the distribution.

Let 𝜇 𝑎𝑛𝑑 𝜎 be the mean and S.D of the normal distribution.

By data 𝑃(𝑥 < 45) = 0.31 𝑎𝑛𝑑 𝑃(𝑥 > 64) = 0.08
𝑥−𝜇
We have, Standard normal variate (S.N.V) 𝑧 = 𝜎
45−𝜇
When 𝑥 = 45, 𝑧 = = 𝑧1 (say)
𝜎
64−𝜇
𝑥 = 64, 𝑧 = = 𝑧2 (say)
𝜎

Thus we have,
𝑃(𝑧 < 𝑧1 ) = 0.31 and 𝑃(𝑧 > 𝑧2 ) = 0.08
0.5 +𝐴(𝑧1 ) = 0.31 and 0.5 - 𝐴(𝑧2 ) = 0.08
𝐴(𝑧1 ) = −0.19 and 𝐴(𝑧2 ) = 0.42
Refering to the normal probability distribution tables, we have
0.1915(≈ 0.19) = 𝐴(0.5) 𝑎𝑛𝑑 0.4192(≈ 0.42) = 𝐴(1.4)
𝐴(𝑧1 ) = −𝐴(0.5) and 𝐴(𝑧2 ) = 𝐴(1.4)
𝑧1 = −0.5 𝑎𝑛𝑑 𝑧2 = 1.4
45−𝜇 64−𝜇
𝑖. 𝑒. = 𝑧1 and = 𝑧2
𝜎 𝜎
45−𝜇 64−𝜇
𝑖. 𝑒. = −0.5 and = 1.4
𝜎 𝜎

Or 𝜇 − 0.5𝜎 = 45 and 𝜇 + 1.4𝜎 = 64

By solving we get, mean(𝜇)=50 and S.D =10

6. In an examination 7% of students score less than 35% marks and 89% of students score less than
60% marks. Find the mean and S.D. if the marks are normally distributed.
(Given: P(0 < z <1.2263) = 0.39 and P(0 < z <1.4757) = 0.43)

Let 𝜇 𝑎𝑛𝑑 𝜎 be the mean and S.D of the normal distribution.

By data 𝑃(𝑥 < 35) = 0.07 𝑎𝑛𝑑 𝑃(𝑥 < 60) = 0.89
𝑥−𝜇
We have, Standard normal variate (S.N.V) 𝑧 = 𝜎
35−𝜇
When 𝑥 = 35, 𝑧 = = 𝑧1 (say)
𝜎
 60−𝜇
𝑥 = 60, 𝑧 = = 𝑧2 (say)
𝜎

Thus we have,
𝑃(𝑧 < 𝑧1 ) = 0.07 and 𝑃(𝑧 < 𝑧2 ) = 0.89
0.5 +𝐴(𝑧1 ) = 0.07 and 0.5 + 𝐴(𝑧2 ) = 0.89
𝐴(𝑧1 ) = −0.43 and 𝐴(𝑧2 ) = 0.39
Refering to the normal probability distribution tables, we have
0.43 = 𝐴(1.475) 𝑎𝑛𝑑 0.39 = 𝐴(1.226)
𝐴(𝑧1 ) = −𝐴(1.4757) and 𝐴(𝑧2 ) = 𝐴(1.2263)
𝑧1 = −1.4757 𝑎𝑛𝑑 𝑧2 = 1.2263
35−𝜇 60−𝜇
𝑖. 𝑒. = 𝑧1 and = 𝑧2
𝜎 𝜎
35−𝜇 60−𝜇
𝑖. 𝑒. = −1.4757 and = 1.2263
𝜎 𝜎

Or 𝜇 − 1.4757𝜎 = 35 and 𝜇 + 1.2263𝜎 = 60

By solving we get, mean(𝜇)=48.65 and S.D =9.25