Module I : Probability Distributions

Topic 1: Review of basic probability theory. Random

variables, Probability mass and density functions.
Mathematical expectation, Mean and Variance.

Dr. P. Rajendra, Professor, Department of mathematics,

CMRIT, Bengaluru.
Basic Probability Theory
▶ Probability is a measure of the likelihood of an event
occurring.
▶ For any event A, the probability of A is denoted by P(A),
where 0 ≤ P(A) ≤ 1.
▶ The sum of probabilities of all possible outcomes in a sample
space is 1.
▶ Conditional Probability: The probability of event A given
that event B has occurred is P(A | B) = P(A∩B)
P(B) , assuming
P(B) > 0.
▶ Independence: Two events A and B are independent if
P(A ∩ B) = P(A)P(B).

Example
Consider a spam detection model where A is the event ”email
contains the word ’free’” and B is the event ”email is spam”.
Understanding P(B | A) helps in improving the accuracy of the
model.
Random Variables

▶ A Random Variable is a function that assigns a numerical

value to each outcome in a sample space.
▶ Random variables can be discrete or continuous.
▶ Discrete Random Variables take on a countable number of
distinct values.
▶ Continuous Random Variables take on an uncountable
number of values within an interval.

Example
In a recommendation system, let X be a discrete random variable
representing the number of clicks on recommended items. A
continuous random variable Y might represent the time a user
spends on a page.
Mathematical Expectation (Expected Value)
▶ The Expected Value or Expectation of a random variable is
the long-run average value of repetitions of the experiment it
represents.
▶ For a discrete random variable X with PMF P(X = xi ) = pi ,
the expectation is:
X
E [X ] = xi · pi
i

▶ For a continuous random variable X with PDF f (x), the

expectation is: Z ∞
E [X ] = x · f (x) dx
−∞

Example
In an e-commerce setting, X could represent the revenue generated
per user. The expected revenue, E [X ], is a crucial metric for
decision-making.
Mean
▶ The Mean of a random variable is another term for its
expected value and provides a measure of the central
tendency of the distribution.
▶ For a discrete random variable X :
X
µ = E [X ] = x i · pi
i

▶ For a continuous random variable X :

Z ∞
µ = E [X ] = x · f (x) dx
−∞

Example
In a user engagement model, the mean number of interactions per
session can inform interface design and content placement.
Variance
▶ The Variance of a random variable is a measure of how much
the values of the random variable differ from the mean.
▶ For a discrete random variable X :
X
Var(X ) = E [(X − µ)2 ] = (xi − µ)2 · pi
i

▶ For a continuous random variable X :

Z ∞
2
Var(X ) = E [(X − µ) ] = (x − µ)2 · f (x) dx
−∞

▶ The square root of the variance is the standard deviation,

which gives a measure of spread in the same units as the
random variable.
Example
In a predictive model, understanding the variance of predictions
(e.g., predicted sales) helps in assessing the reliability and
confidence in those predictions.
Probability Mass Function (PMF)
The Probability Mass Function(PMF) is the probability distribution
of a discrete random variable and provides the possible values and
their associated probabilities.
1. P(xi ) ≥ 0
Pn
2. i=1 P(X = xi ) = 1
3. 0 ≤ P(x) ≤ 1
4. Mean(µ):
n
X
µ = E [X ] = xi P(xi )
i=1

5. Variance(σ 2 ):
n
X
σ2 = xi2 P(xi ) − µ2 or σ 2 = E [X 2 ] − (E [X ])2
i=1
Probability Density Function (PDF)
The Probability Density Function (PDF) is the probability
distribution of a continuous random variable and provides the
possible values and their associated probabilities infinitely.
1. P(xi ) ≥ 0 or f (x) ≥ 0
R∞
2. −∞ f (x) dx = 1
3. Mean (µ): Z ∞
µ= xf (x) dx
−∞
4. Variance (σ 2 ):
Z ∞
2
σ = x 2 f (x) dx − µ2
−∞

5. Probability over an interval:

P(a ≤ x ≤ b) = P(a < x ≤ b)
Z b
= P(a ≤ x < b) = P(a < x < b) = f (x) dx
a
Problem 1

Show that the following probabilities satisfy the properties of a

discrete random variable. Hence, find the mean and variance.
x 0 1 2 3
1 3 3 1
P(x) 8 8 8 8

Solution: To verify that P(x) satisfies the properties of a discrete

random variable, we need to check two conditions:
(i) P(xi ) ≥ 0 for all i.
P
(ii) i P(xi ) = 1.
(i). Non-negativity:
 
1 3 3 1
P(x) = , , , ≥0
8 8 8 8
(ii). Sum of probabilities equals 1:
X 1 3 3 1 8
P(x) = + + + = =1
x
8 8 8 8 8
Since both conditions are satisfied, P(x) represents a valid discrete
probability distribution.
The mean (µ) of a discrete random variable is given by:
X
µ = E [X ] = x · P(x)
x
Calculating the mean:
1 3 3 1
µ=0· +1· +2· +3·
8 8 8 8
3 6 3 12
µ=0+ + + = = 1.5
8 8 8 8
The variance (σ 2 ) is given by:

σ 2 = E [X 2 ] − (E [X ])2
First, find E [X 2 ]:
X
E [X 2 ] = x 2 · P(x)
x

Calculating E [X 2 ]:
1 3 3 1
E [X 2 ] = 02 · + 12 · + 2 2 · + 32 ·
8 8 8 8
3 12 9 24
E [X 2 ] = 0 + + + = =3
8 8 8 8
Now, calculate the variance:

σ 2 = E [X 2 ] − (E [X ])2 = 3 − (1.5)2 = 3 − 2.25 = 0.75

Thus, the mean is µ = 1.5 , the variance is σ 2 = 0.75 and S.D is
σ = 0.86.
Problem 2
Find the value of k such that the following distribution represents
a discrete probability distribution. Hence, find the Mean, Standard
Deviation, 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:
The sum of all probabilities must equal 1 for it to be a valid
probability distribution:

k + 2k + 3k + 4k + 3k + 2k + k = 1

16k = 1
1
k=
16
The mean µ is given by:
X
µ = E [X ] = xi · P(xi )
i

Substituting the values:

1 2 3 4 3 2 1
µ = (−3) · + (−2) · + (−1) · + 0 · + 1 · + 2 · + 3 ·
16 16 16 16 16 16 16
−3 − 4 − 3 + 0 + 3 + 4 + 3 0
µ= = =0
16 16
The variance σ 2 is given by:

σ 2 = E [X 2 ] − (E [X ])2

First, compute E [X 2 ]:
X
E [X 2 ] = xi2 · P(xi )
i
 1 2 3
E [X 2 ] = (−3)2 · + (−2)2 · + (−1)2 · + 02
16 16 16
4 3 2 1
· + 12 · + 22 · + 32 ·
16 16 16 16
9 + 8 + 3 + 0 + 3 + 8 + 9 40
E [X 2 ] = = = 2.5
16 16
Since µ = 0:
σ 2 = 2.5 − 02 = 2.5
√
σ = 2.5 ≈ 1.58
P(x ≤ 1) = P(−3) + P(−2) + P(−1) + P(0) + P(1)
1 13
∴ P(x ≤ 1) = k + 2k + 3k + 4k + 3k = 13k = 13 × =
16 16
1 3
P(x > 1) = P(2) + P(3) = 2k + k = 3k = 3 × =
16 16
1 9
= P(0) + P(1) + P(2) = 4k + 3k + 2k = 9k = 9 × =
16 16
Problem 3

A random variable X has a probability function for various values

of x as given below:

x 0 1 2 3 4 5 6 7
P(x) 0 k 2k 2k 3k k2 2k2 7k2+k

Find:
(i) k
(ii) P(x < 6)
(iii) P(x ≥ 6)
(iv) P(3 < x ≤ 6)
Solution: To find the value of k, we use the fact that the total
probability must equal 1:

0 + k + 2k + 2k + 3k + k 2 + 2k 2 + (7k 2 + k) = 1
Simplifying this, we have:

10k + 10k 2 − k = 1
This simplifies to:

10k 2 + 9k − 1 = 0
√
2
b −4ac
Using the quadratic formula k = −b± 2a , where a = 10,
b = 9, and c = −1, we find:
p √
−9 ± 92 − 4 · 10 · (−1) −9 ± 81 + 40
k= =
2 · 10 20
 √
−9 ± 121
k=
20
−9 ± 11
k=
20
So, the two possible values for k are:

1
k= = 0.1(we have k = -1 also, but k must be positive)
10
Now, calculate the probabilities:
ii) P(x < 6) = P(0) + P(1) + P(2) + P(3) + P(4) + P(5) =
0 + k + 2k + 2k + 3k + k 2 = 8k + k 2
iii) P(x ≥ 6) = P(6) + P(7) = 2k 2 + (7k 2 + k) = 9k 2 + k
iv) P(3 < x ≤ 6) = P(4)+P(5)+P(6) = 3k +k 2 +2k 2 = 3k +3k 2
Using k = 0.1:

P(x < 6) = 8(0.1) + (0.1)2 = 0.8 + 0.01 = 0.81

P(x ≥ 6) = 9(0.1)2 + 0.1 = 0.09 + 0.1 = 0.19
P(3 < x ≤ 6) = 3(0.1) + 3(0.1)2 = 0.3 + 0.03 = 0.33
Problem 4

Show that the function

(
e −x , x ≥ 0
f (x) =
0, x <0
is a probability density function (PDF). Hence, find
P(1.5 < x < 2.5).

Solution:
To show that f (x) is a probability density function, it must satisfy
two conditions:
1. f (x) ≥ 0 for all x.
2. The total integral of f (x) over all x must equal 1.
(i). Non-negativity:

f (x) = e −x ≥ 0 for all x ≥0

(ii). Integral equals 1:
Z ∞ Z ∞
f (x) dx = e −x dx
−∞ 0
Z ∞ ∞
e −x dx = −e −x 0 = (0 − (−1)) = 1

∴
0
Since both conditions are satisfied, f (x) is a valid probability
density function.
 Z 2.5
P(1.5 < x < 2.5) = e −x dx
1.5
Calculate the integral:
Z 2.5 2.5
e −x dx = −e −x 1.5

1.5

= −e −2.5 + e −1.5

= e −1.5 − e −2.5

1 1
= −
e 1.5 e 2.5
Thus,
1 1
P(1.5 < x < 2.5) = −
e 1.5 e 2.5
Problem 5

A random variable X has a probability density function (PDF)

given by:
(
kx 2 , 0 ≤ x ≤ 3
f (x) =
0, otherwise
Evaluate:
(i) k
(ii) P(x ≤ 1)
(iii) P(x > 1)
(iv) P(1 ≤ x ≤ 2)
(v) P(x ≤ 2)
(vi) P(x ≥ 2)
Solution:
The total probability must be equal to 1, so:
Z ∞ Z 3
f (x) dx = kx 2 dx = 1
−∞ 0

3 3
x3
Z   
27
∴k x 2 dx = k =k −0 = 9k
0 3 0 3
So,
1
9k = 1 =⇒ k =
9
ii) P(x ≤ 1):
Z 1 Z 1
1 2
P(x ≤ 1) = f (x) dx = x dx
0 0 9
 1
1 x3 1 1 1
∴ = · =
9 3 0 9 3 27
iii) P(x > 1):
1 26
P(x > 1) = 1 − P(x ≤ 1) = 1 − =
27 27
iv) P(1 ≤ x ≤ 2):
Z 2 Z 2
1 2
P(1 ≤ x ≤ 2) = f (x) dx = x dx
1 1 9
3 2
   
1 x 1 8 1 1 7 7
∴ = − = · =
9 3 1 9 3 3 9 3 27
v) P(x ≤ 2):
Z 2 Z 2
1 2
P(x ≤ 2) = f (x) dx = x dx
0 0 9
3 2
 
1 x 1 8 8
∴ = · =
9 3 0 9 3 27
vi) P(x ≥ 2):
8 19
P(x ≥ 2) = 1 − P(x ≤ 2) = 1 − =
27 27
Problem 6
The diameter of an electric cable is assumed to be a continuous
random variable with a probability density function (PDF) given by:
(
kx(1 − x), 0 ≤ x ≤ 1
f (x) =
0, otherwise
Find:
(i) The value of k.
(ii) The Mean and Variance.

Solution:
The total probability must be equal to 1:
Z ∞ Z 1
f (x) dx = kx(1 − x) dx = 1
−∞ 0
 Z 1 Z 1 Z 1 
2
∴k x(1 − x) dx = k x dx − x dx
0 0 0
1 1 !
x2 x3
   
1 1
k − =k −
2 0 3 0 2 3
   
3 2 1
k − =k
6 6 6
k
= 1 =⇒ k = 6
6
The mean µ is given by:
Z ∞ Z 1
µ = E [X ] = xf (x) dx = x · 6x(1 − x) dx
−∞ 0
 Z 1 Z 1 Z 1 
2 2 3
∴6 x (1 − x) dx = 6 x dx − x dx
0 0 0
1 !
1
x4
x3
   
1 1
6 − =6 −
0 34 0 3 4
   
4 3 1 6 1
6 − =6 = =
12 12 12 12 2
Thus, the mean µ = 12 .
The variance σ 2 is given by:

σ 2 = E [X 2 ] − (E [X ])2
 Z ∞ Z 1
E [X 2 ] = x 2 f (x) dx = x 2 · 6x(1 − x) dx
−∞ 0
Z 1 Z 1 Z 1 
3 3 4
6 x (1 − x) dx = 6 x dx − x dx
0 0 0
1 !
1
x4x5
  
1 1
6 − =6 −
0 4 5 0 4 5
   
5 4 1 6 3
6 − =6 = =
20 20 20 20 10
3
So, E [X 2 ] = 10 .
 2
2 3 1 3 1 3 2.5 0.5 1
σ = − = − = − = =
10 2 10 4 10 10 10 20
1
Thus, the variance σ 2 = 20 .
Assignment Problems (DRV)
1. Find the value of k such that the following distribution
represents a discrete probability distribution. Hence, find the
Mean, S.D, P(x ≥ 5), and P(3 < x ≤ 6). [Ans: (i) k=1/49,
Mean = 4.14, S.D = 1.64, (ii) 0.48 (iii) 0.67]
x 0 1 2 3 4 5 6
P(x) k 3k 5k 7k 9k 11k 13k
2. A random variable has the following probability function for
the various values of X = x. Find i) the value of k, ii)
P(x < 1), iii) P(x ≥ 1). [Ans: (i) k=0.1 (ii) 0.4 (iii) 0.9]
x -2 -1 0 1 2 3
P(x) 0.1 k 0.2 2k 0.3 k
3. A random variable has the following probability function for
the various values of X = x. Find i) the value of k, ii)
P(x ≤ 1), iii) P(0 ≤ x < 3). [Ans: (i) k=1/32 (ii) 0.18 (iii)
0.5]
x 0 1 2 3 4 5
P(x) k 5k 10k 10k 5k k
Assignment Problems (CRV)
1. A random variable X has the probability density function
(PDF):
(
kx 2 , −3 ≤ x ≤ 3
f (x) =
0, otherwise
Find:
i) k [Ans:1/18]
ii) P(x ≤ 2) [Ans:35/54]
iii) P(x ≥ 2) [Ans:19/54]
iv) P(x > 1) [Ans:26/54]
v) P(1 ≤ x ≤ 2) [Ans:7/54]
2. Find the constant k such that
(
kxe −x , 0 < x < 1
f (x) =
0, otherwise
is a valid probability density function (PDF). Find the mean.
[Ans: (i)k=e/(e-2) (ii)=(2e-5)/(e-2)]
 Module I: Probability Distributions
Topic 2: Binomial Distribution

Dr. P. Rajendra, Professor, Department of Mathematics,

CMRIT, Bengaluru.
Introduction to Binomial Distribution

▶ The Binomial Distribution is a discrete probability

distribution that models the number of successes in a fixed
number of independent Bernoulli trials.
▶ Each trial has two possible outcomes: success (with
probability p) or failure (with probability 1 − p).
▶ The Binomial Distribution is characterized by two parameters:

▶ n: The number of trials.

▶ p: The probability of success on each trial.

Example
In a binary classification problem, the Binomial Distribution can
model the number of correct predictions (successes) out of n total
predictions made by a machine learning model.
Binomial Distribution(Continued..)
Let X be a discrete random variable, p be the probability of
success, and q be the probability of failure. The probability mass
function of the binomial distribution can be defined as:
(

n x n−x
x p q , x ≥0
P(X = x) = b(n, p, x) =
0, Otherwise
where n is the number of trials and n p are the parameters.

The binomial distribution follows the following properties:

1. P(X = x) = b(n, p, x) ≥ 0
2. p
P+ q =
1
n n x n−x
3. x=0 x p q =1

The mean, variance, and standard deviation of the binomial

distribution are given by:
▶ Mean: µ = np
▶ Variance: σ 2 = npq
√
▶ Standard Deviation: σ = npq
Applications in AI and Data Science

▶ Model Evaluation: The Binomial Distribution is used to

model the number of successes (correct predictions) in a fixed
number of trials (predictions).
▶ A/B Testing: In A/B testing, it can model the number of
users who perform a specific action (e.g., click a button) out
of a total number of users exposed to the variant.
▶ Natural Language Processing (NLP): Used to model the
occurrence of a particular word in a fixed number of text
documents.
▶ Spam Detection: Can model the number of spam emails
correctly identified out of a set number of emails.
Derivation for Mean, Variance of a Binomial Random
Variable

Let X be a binomial random variable with parameters n (number

of trials) and p (probability of success). The probability mass
function (PMF) of X is given by:
 
n x n−x
P(X = x) = p q , x = 0, 1, 2, . . . , n
x

where q = 1 − p.
The mean (expected value) µX of X is defined as:
n
X
µX = E (X ) = x · P(X = x)
x=0

Substituting the PMF:

n  
X n x n−x
µX = x p q
x
x=0

We can express this as:

n  
X n − 1 x−1 (n−1)−(x−1)
µX = np p q
x −1
x=1

Letting y = x − 1, the sum becomes:

n−1  
X n − 1 y (n−1)−y
µX = np p q = np(p + q)n−1
y
y =0

Since p + q = 1, we have: µX = np
To find the variance, we first calculate E (X (X − 1)):
n
X
E (X (X − 1)) = x(x − 1) · P(X = x)
x=0
Substituting the PMF:
n  
X n x n−x
E (X (X − 1)) = x(x − 1) p q
x
x=0
This can be simplified as:
n  
X n − 2 x−2 (n−2)−(x−2)
2
E (X (X − 1)) = n(n − 1)p p q
x −2
x=2
Letting y = x − 2, the sum becomes:
n−2  
2
X n − 2 y (n−2)−y
E (X (X −1)) = n(n−1)p p q = n(n−1)p 2 (p+q)n−2
y
y =0

Since p + q = 1, we have:
E (X (X − 1)) = n(n − 1)p 2
The variance σX2 of X is given by:
σX2 = E (X 2 ) − (E (X ))2
Expanding E (X 2 ):
E (X 2 ) = E (X (X − 1)) + E (X )
Substituting the values:
σX2 = n(n − 1)p 2 + np − (np)2
Simplifying:
σX2 = np(1 − p) = npq
σX2 = npq.
Standard Deviation of the Binomial Distribution
The standard deviation σX is the square root of the variance:
√
σX = npq
Thus, the standard deviation of the binomial distribution is
√
σX = npq.
Problem 1

Let X be a binomially distributed random variable based on 6

repetitions of an experiment with probability of success p = 0.3.
Evaluate the following probabilities: (i)P(X ≤ 3), (ii)P(X > 4)

Solution: The probability mass function of a binomial random

variable X with parameters n and p is given by:
 
n k
P(X = k) = p (1 − p)n−k
k
where n = 6 and p = 0.3.
(i). Calculate P(X ≤ 3):

P(X ≤ 3) = P(X = 0) + P(X = 1) + P(X = 2) + P(X = 3)

 
6
P(X = 0) = (0.3)0 (0.7)6 = 1 · 1 · (0.7)6 = (0.7)6
0
 
6
P(X = 1) = (0.3)1 (0.7)5 = 6 · (0.3) · (0.7)5
1
 
6
P(X = 2) = (0.3)2 (0.7)4 = 15 · (0.3)2 · (0.7)4
2
 
6
P(X = 3) = (0.3)3 (0.7)3 = 20 · (0.3)3 · (0.7)3
3

∴ P(X ≤ 3) = (0.7)6 +6·0.3·(0.7)5 +15·(0.3)2 ·(0.7)4 +20·(0.3)3 ·(0.7)3

P(X ≤ 3) ≈ 0.1176 + 0.3025 + 0.3241 + 0.1852 = 0.9294

(ii). Calculate P(X > 4):

P(X > 4) = P(X = 5) + P(X = 6)

 
6
P(X = 5) = (0.3)5 (0.7)1 = 6 · (0.3)5 · (0.7)
5
 
6
P(X = 6) = (0.3)6 (0.7)0 = 1 · (0.3)6 · 1
6

∴ P(X > 4) = 6 · (0.3)5 · (0.7) + (0.3)6

P(X > 4) ≈ 0.0102 + 0.0007 = 0.0109

Thus,

P(X ≤ 3) ≈ 0.9294, P(X > 4) ≈ 0.0109.

Problem 2

The probability that a pen manufactured by a company will be

defective is 0.1. If 12 such pens are selected at random, find the
probability that: (i) Exactly 2 pens will be defective, (ii) At most 2
pens will be defective, (iii) None will be defective.

Solution: Given that the probability of a pen being defective is

p = 0.1, and the number of pens selected is n = 12, we use the
binomial distribution formula:
 
n k
P(X = k) = p (1 − p)n−k
k
where X is the random variable representing the number of
defective pens.
(i). Probability that exactly 2 pens will be defective
 
12
P(X = 2) = (0.1)2 (0.9)10
2
Calculate 12


2 :
 
12 12! 12 · 11
= = = 66
2 2!(12 − 2)! 2·1
Then:

P(X = 2) = 66 · (0.1)2 · (0.9)10

P(X = 2) = 66 · 0.01 · 0.3487 = 0.2301

(ii). Probability that at most 2 pens will be defective

P(X ≤ 2) = P(X = 0) + P(X = 1) + P(X = 2)

Calculate each term:
 
12
P(X = 0) = (0.1)0 (0.9)12 = 1 · 1 · (0.9)12 = (0.9)12
0

P(X = 0) = (0.9)12 = 0.2824

 
12
P(X = 1) = (0.1)1 (0.9)11 = 12 · 0.1 · (0.9)11
1

P(X = 1) = 0.3766

∴, P(X ≤ 2) = 0.2824 + 0.3766 + 0.2301 = 0.8891

(iii). Probability that none will be defective (P(X = 0))

P(X = 0) = (0.9)12 = 0.2824

Problem 3

The number of telephonic lines busy at an instant is a binomial

variant with a probability of 0.1. If 10 lines are chosen at random,
what is the probability that: (i) No line is busy, (ii) All lines are
busy, (iii) At least one line is busy, (iv) At most two lines are busy.

Solution: Given that the probability of a line being busy is

p = 0.1, and the number of lines chosen is n = 10, we use the
binomial distribution formula:
 
n k
P(X = k) = p (1 − p)n−k
k
where X is the random variable representing the number of busy
lines.
(i). Probability that no line is busy (P(X = 0))
 
10
P(X = 0) = (0.1)0 (0.9)10
0
Calculate P(X = 0):

P(X = 0) = 1 · 1 · (0.9)10 = (0.9)10

P(X = 0) ≈ 0.3487
(ii). Probability that all lines are busy (P(X = 10))
 
10
P(X = 10) = (0.1)10 (0.9)0
10
Calculate P(X = 10):

P(X = 10) = 1 · (0.1)10 · 1 = (0.1)10

P(X = 10) = 10−10 ≈ 10−10 ≈ 0.0000000001

(iii). Probability that at least one line is busy (P(X ≥ 1))

P(X ≥ 1) = 1 − P(X = 0)
Using the value of P(X = 0) calculated earlier:

P(X ≥ 1) = 1 − 0.3487 = 0.6513

(iv). Probability that at most two lines are busy (P(X ≤ 2))

P(X ≤ 2) = P(X = 0) + P(X = 1) + P(X = 2)

Calculate P(X = 1) and P(X = 2):
 
10
P(X = 1) = (0.1)1 (0.9)9 = 10 · 0.1 · (0.9)9
1

P(X = 1) = 10 · 0.1 · 0.3874 = 0.3874

 
10
P(X = 2) = (0.1)2 (0.9)8 = 45 · 0.01 · (0.9)8
2

P(X = 2) = 45 · 0.01 · 0.4305 = 0.1937

Add these probabilities:

P(X ≤ 2) = 0.3487 + 0.3874 + 0.1937 = 0.9298

Problem 4

When a coin is tossed 4 times, find the probability of getting: (i)

Exactly one head, (ii) At most three heads, (iii) At least two heads.

Solution: Given that a coin is tossed 4 times, we have a binomial

distribution with n = 4 and probability of getting a head p = 0.5.
The binomial probability formula is:
 
n k
P(X = k) = p (1 − p)n−k
k
where X is the random variable representing the number of heads.
(i). Probability of getting exactly one head (P(X = 1))
 
4
P(X = 1) = (0.5)1 (0.5)4−1
1
Calculate P(X = 1):

P(X = 1) = 4 · (0.5)1 · (0.5)3 = 4 · 0.5 · 0.125 = 0.25

(ii). Probability of getting at most three heads (P(X ≤ 3))

P(X ≤ 3) = P(X = 0) + P(X = 1) + P(X = 2) + P(X = 3)

Calculate each term:
 
4
P(X = 0) = (0.5)0 (0.5)4 = 1 · 1 · 0.0625 = 0.0625
0
 
4
P(X = 2) = (0.5)2 (0.5)2 = 6 · 0.25 · 0.25 = 0.375
2
 
4
P(X = 3) = (0.5)3 (0.5)1 = 4 · 0.125 · 0.5 = 0.25
3
Add these probabilities:

P(X ≤ 3) = 0.0625 + 0.25 + 0.375 + 0.25 = 0.9375

(iii). Probability of getting at least two heads (P(X ≥ 2))

P(X ≥ 2) = 1 − P(X < 2) = 1 − (P(X = 0) + P(X = 1))

Using the values calculated earlier:

P(X < 2) = P(X = 0) + P(X = 1) = 0.0625 + 0.25 = 0.3125

P(X ≥ 2) = 1 − 0.3125 = 0.6875

Assignment Problems
1. The probability of germination of a seed in a packet of seeds
is found to be 0.7. If 10 seeds are taken for experimenting on
germination in a laboratory, find the probability that: (i) 8
seeds germinate. [Ans: 0.2334], (ii) At least 8 seeds
germinate. [Ans: 0.3826], (iii) At most 8 seeds germinate.
[Ans: 0.8508]
2. A communication channel receives independent pulses at the
rate of 12 pulses per microsecond. The probability of
transmission error is 0.001 for each microsecond. Compute
the probability of: (i) No error during a microsecond. [Ans:
0.9880], (ii) 1 error. [Ans: 0.0118], (iii) At least 1 error. [Ans:
0.0120], (iv) 2 errors. [Ans: 0.000065], (v) At most 2 errors.
[Ans: 0.9999]
3. In 800 families with 5 children each, how many families would
be expected to have: (i) 3 boys. [Ans: 250], (ii) 5 girls. [Ans:
25], (iii) At most 2 girls. [Ans: 400], (v) Either 2 or 3 boys.
[Ans: 500], [Note:- Assuming the probability for boys and girls
to be equal.]
 Module I: Probability Distributions
Topic 3: Poisson Distribution

Dr. P. Rajendra, Professor, Department of Mathematics,

CMRIT, Bengaluru.
Introduction to Poisson Distribution

▶ The Poisson Distribution is a discrete probability

distribution that expresses the probability of a given number
of events occurring in a fixed interval of time or space.
▶ The key assumptions are:
▶ Events occur independently of each other.
▶ The average rate (λ) at which events occur is constant.
▶ Two events cannot occur at exactly the same time.
▶ The Poisson Distribution is particularly useful for modeling
the number of times an event occurs within a specific time
period or spatial area.

Example
The Poisson Distribution can model the number of user clicks on a
webpage per minute or the number of requests to a server per hour.
Poisson Distribution (Continued..)
▶ The probability mass function (PMF) of the Poisson
Distribution is given by:

λk e −λ
P(X = k) =
k!
▶ Here:
▶ X is the random variable representing the number of events.
▶ k is the actual number of events that occur.
▶ λ is the average rate (mean number of events in the interval).
▶ e is the base of the natural logarithm (approximately 2.71828).
▶ The PMF gives the probability of observing exactly k events
in a fixed interval.

Example
Suppose a server receives an average of 5 requests per minute.
The Poisson Distribution can be used to find the probability that
the server receives exactly 8 requests in a given minute.
Poisson Distribution (Continued..)

Let X be the discrete random variable for any real value λ, such
that the probability mass function of the Poisson distribution can
be defined as:
( −λ x
e λ
P(X = x) = P(x) = x! , x ≥ 0
0, otherwise
where λ is called the parameter.
i) P(X = x) = P(x) ≥ 0
P∞ P∞ e −λ λx
ii) x=0 P(x) = x=0 x! =1
iii) Mean, µ = np = λ
√
iv) Variance, σ 2 = λ, S.D = λ
Relationship to Other Distributions

▶ The Poisson Distribution can be derived as a limiting case of

the Binomial Distribution when the number of trials n
becomes large and the probability of success p becomes small,
such that np = λ remains constant.
▶ For large values of λ, the Poisson Distribution approaches a
Normal Distribution due to the Central Limit Theorem.

Example
If a machine learning model is evaluated over a large dataset with
rare events (such as detecting rare failures), the distribution of the
number of detected failures might be approximated by a Poisson
Distribution.
Applications in AI and Data Science

▶ Event Prediction: The Poisson Distribution is used to

predict the number of events (e.g., clicks, purchases, or
system failures) within a specific time frame.
▶ Anomaly Detection: In network security, the Poisson
Distribution can model the normal number of requests to a
server. Significant deviations might indicate anomalies.
▶ Natural Language Processing (NLP): Used to model the
number of times a rare word occurs in a large text corpus.
▶ Queueing Theory: The Poisson Distribution models the
number of arrivals of jobs or tasks in systems like customer
service queues or server request handling.
Derivation for Mean and Variance of a Poisson Distribution
Let X be a random variable following a Poisson distribution with
parameter λ. The probability mass function (pmf) of X is given by:

e −λ λx
P(X = x) = , x = 0, 1, 2, . . .
x!
1. Mean of a Poisson Distribution
The mean (expected value) E (X ) of a Poisson distribution can be
derived as follows:
∞ ∞
X X e −λ λx
E (X ) = x · P(X = x) = x·
x!
x=0 x=0
λx
Rewriting x as x = x · x(x−1)! , we have:
∞
X λx
E (X ) = e −λ
(x − 1)!
x=1
Let y = x − 1, then x = y + 1 and as x goes from 1 to ∞, y goes
from 0 to ∞:
 ∞
X λy
E (X ) = e −λ λ
y!
y =0
P∞ λy
Using the fact that y =0 y ! = e λ , we get:

E (X ) = e −λ λe λ = λ
Therefore, the mean of a Poisson distribution is:

E (X ) = λ
2. Variance of a Poisson Distribution
The variance Var(X ) of a Poisson distribution is given by
E (X 2 ) − [E (X )]2 .
First, we find E (X 2 ):
∞ ∞
X X e −λ λx
E (X 2 ) = x 2 · P(X = x) = x2 ·
x!
x=0 x=0
Rewriting x 2 as x(x − 1) + x, we have:
∞ ∞
−λ
X λx X λx−1
2
E (X ) = e + e −λ λ
(x − 2)! (x − 1)!
x=2 x=1

Letting y = x − 2 and z = x − 1, we get:

∞ ∞
X λy X λz
E (X 2 ) = e −λ λ2 + e −λ λ
y! z!
y =0 z=0

E (X 2 ) = λ2 + λ
Then, the variance is:

Var(X ) = E (X 2 ) − [E (X )]2 = (λ2 + λ) − λ2 = λ

Thus, the variance of a Poisson distribution is:

Var(X ) = λ
Problem 1

The number of accidents in a year for taxi drivers in a city follows

a Poisson distribution with a mean of 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:
Given that X follows a Poisson distribution with mean λ = 3.

e −λ λx
P(X = x) =
x!
where λ = 3.
(i) Number of drivers with no accident in a year:

e −3 · 30
P(X = 0) = = e −3 ≈ 0.0498
0!
The expected number of drivers with no accidents is:

1000 × P(X = 0) = 1000 × 0.0498 = 49.8 ≈ 50

So, approximately 50 drivers are expected to have no accidents in a
year.

(ii). Number of drivers with more than 3 accidents in a year:

We need to calculate P(X > 3), which is:

P(X > 3) = 1 − P(X ≤ 3)

First, calculate P(X ≤ 3):

P(X ≤ 3) = P(X = 0) + P(X = 1) + P(X = 2) + P(X = 3)

 30
P(X = 0) = e −3 = e −3 ≈ 0.0498
0!
31
P(X = 1) = e −3 = 3e −3 ≈ 0.1494
1!
3 2 9e −3
P(X = 2) = e −3 = ≈ 0.2240
2! 2
33 27e −3
P(X = 3) = e −3 = ≈ 0.2240
3! 6
P(X ≤ 3) ≈ 0.0498 + 0.1494 + 0.2240 + 0.2240 = 0.6472
Thus,

P(X > 3) = 1 − 0.6472 = 0.3528

The expected number of drivers with more than 3 accidents is:

1000 × P(X > 3) = 1000 × 0.3528 = 352.8 ≈ 353

So, approximately 353 drivers are expected to have more than 3
accidents in a year.
Problem 2
In a certain factory turning out razor blades, there is a small
1
probability of 500 for any blade to be defective. The blades are
supplied in packets of 10. Use the Poisson distribution to calculate
the approximate number of packets containing:
(i) No defective blades.
(ii) 2 defective blades.
(iii) 3 defective blades.
in the consignment of 10,000 packets.

Solution:
Let X denote the number of defective blades in a packet. The
1
probability of a blade being defective is p = 500 . The mean
number of defective blades per packet, λ, can be calculated as:
1 10
λ = np = 10 × = = 0.02
500 500
The Poisson probability mass function is given by:

e −λ λx
P(X = x) =
x!
where λ = 0.02.

(i). Number of packets with no defective blades:

e −0.02 · 0.020
P(X = 0) = = e −0.02 ≈ 0.9802
0!
The expected number of packets with no defective blades is:

10000 × P(X = 0) = 10000 × 0.9802 = 9802

So, approximately 9802 packets are expected to have no defective
blades.
(ii). Number of packets with 2 defective blades:

e −0.02 · 0.022
P(X = 2) =
2!
e −0.02 · 0.0004 0.9802 × 0.0004
= ≈ = 0.000196
2 2
The expected number of packets with 2 defective blades is:

10000 × P(X = 2) = 10000 × 0.000196 = 1.96

So, approximately 2 packets are expected to have 2 defective
blades.
(iii). Number of packets with 3 defective blades:

e −0.02 · 0.023
P(X = 3) =
3!
e −0.02 · 0.000008 0.9802 × 0.000008
= ≈ = 0.00000131
6 6
The expected number of packets with 3 defective blades is:

10000 × P(X = 3) = 10000 × 0.00000131 = 0.0131

So, approximately 0 packets are expected to have 3 defective
blades (very unlikely).
Problem 3

If the probability of a bad reaction from a certain injection is

0.001, determine the probability that out of 2000 individuals, more
than 2 will get a bad reaction.

Solution:
Let X denote the number of individuals who get a bad reaction.
The probability of a bad reaction for an individual is p = 0.001.
For 2000 individuals, we have n = 2000.
The mean number of bad reactions, λ, is given by:

λ = np = 2000 × 0.001 = 2
Since n is large and p is small, we can use the Poisson
approximation to the binomial distribution, where X ∼ Poisson(λ).
The probability mass function of a Poisson distribution is:

e −λ λx
P(X = x) =
x!
where λ = 2.
To find the probability that more than 2 individuals will get a bad
reaction, we need to calculate P(X > 2):

P(X > 2) = 1 − P(X ≤ 2)

First, we calculate P(X ≤ 2) using the cumulative distribution
function:

P(X ≤ 2) = P(X = 0) + P(X = 1) + P(X = 2)

Calculating each term:

e −2 · 20
P(X = 0) = = e −2 ≈ 0.1353
0!
 e −2 · 21
P(X = 1) = = 2e −2 ≈ 0.2707
1!

e −2 · 22
P(X = 2) = = 2e −2 ≈ 0.2707
2!
Summing these probabilities:

P(X ≤ 2) = 0.1353 + 0.2707 + 0.2707 = 0.6767

Now, calculate P(X > 2):

P(X > 2) = 1 − 0.6767 = 0.3233

Therefore, the probability that more than 2 individuals will get a
bad reaction is 0.3233.
Assignment Problems
[Link] probability that a news reader commits no mistakes in
reading the news is e13 . Find the probability that on a particular
news broadcast he commits:
(i) Only 2 mistakes [Ans: 0.2240]
(ii) More than 3 mistakes [Ans: 0.3500]
(iii) At most 3 mistakes [Ans: 0.6500]
[Link] 300 misprints are randomly distributed throughout a
book of 500 pages. Find the probability that a given page contains:
(i) Exactly 3 misprints [Ans: 0.0197]
(ii) Less than 3 misprints [Ans: 0.9768]
(iii) 4 or more misprints [Ans: 0.0033]
3. A certain screw-making machine produces an average of 2
defective screws out of 100 and packs them in boxes of 500. Find
the probability that the box contains:
(i) 3 defective screws [Ans: 0.0075]
(ii) At least 1 defective screw [Ans: 0.9999]
(iii) Between 2 and 4 defective screws [Ans: 0.0287]
 Module I: Probability Distributions
Topic 4: Normal Distribution

Dr. P. Rajendra, Professor, Department of Mathematics,

CMRIT, Bengaluru.
Introduction to Normal Distribution
▶ The Normal Distribution, also known as the Gaussian
Distribution, is a continuous probability distribution that is
symmetric about the mean, describing data that clusters
around a central value.
▶ It is characterized by two parameters:
▶ µ (mean): the central value around which the data is
distributed.
▶ σ 2 (variance): the measure of the spread of the distribution.
▶ The Normal Distribution is widely used in statistics, data
science, and AI for modeling natural phenomena, errors, and
noise.

Example
In AI, the Normal Distribution can model the distribution of errors
in predictions made by regression models, or the distribution of
features in a dataset for a machine learning algorithm.
Probability Density Function (PDF)
▶ The probability density function (PDF) of the Normal
Distribution is given by:
(x − µ)2
 
1
f (x) = √ exp −
2πσ 2 2σ 2
▶ Here:
▶ x is the variable.
▶ µ is the mean of the distribution.
▶ σ 2 is the variance of the distribution.
▶ exp is the exponential function.
▶ The PDF describes the likelihood of a random variable taking
on a particular value.
Example
In a machine learning context, the PDF can describe the
distribution of continuous features in a dataset. For instance, if we
assume that the heights of people in a dataset follow a Normal
Distribution, the PDF can tell us the likelihood of finding someone
with a specific height.
Properties of the Normal Distribution
▶ Symmetry: The Normal Distribution is symmetric around the
mean µ.
▶ Mean, Median, and Mode: For a Normal Distribution, the
mean, median, and mode are all equal.
▶ 68-95-99.7 Rule (Empirical Rule):
▶ Approximately 68% of the data lies within one standard
deviation (σ) of the mean.
▶ Approximately 95% of the data lies within two standard
deviations of the mean.
▶ Approximately 99.7% of the data lies within three standard
deviations of the mean.
▶ Unimodal: The distribution has a single peak (mode) at the
mean µ.
Example
When evaluating model performance, the errors or residuals (the
differences between observed and predicted values) are often
assumed to follow a Normal Distribution. This assumption
underlies many statistical tests and confidence intervals.
Standard Normal Distribution
▶ The Standard Normal Distribution is a special case of the
Normal Distribution with a mean of 0 and a standard
deviation of 1.
▶ Any Normal Distribution can be converted to the Standard
Normal Distribution using the z-score:
x −µ
z=
σ
▶ The z-score represents the number of standard deviations a
data point is from the mean.
Applications in AI and Data Science

▶ Regression Analysis: Assumes that the errors or residuals

follow a Normal Distribution, allowing for hypothesis testing
and the construction of confidence intervals.
▶ Data Preprocessing: Features are often normalized to a
Normal Distribution to ensure better model performance,
especially in algorithms sensitive to feature scaling (e.g.,
SVMs, Neural Networks).
▶ Machine Learning Model Assumptions: Some machine
learning algorithms assume normality in data distribution,
impacting how models are trained and evaluated.
▶ Statistical Quality Control: Used in monitoring
manufacturing processes where the measurements of product
quality are normally distributed.
Problem 1
200 students appeared in an examination. The distribution of
marks is assumed to be normal with a mean of 30 and a standard
deviation of 6.25. How many students are expected to get marks:
(i) Between 20 and 40
(i) Less than 35, given that Z (1.6) = 0.4452 and
Z (0.8) = 0.2881

Solution:
Given:
Mean (µ) = 30
Standard Deviation (σ) = 6.25
Total number of students = 200

i) Probability of marks between 20 and 40:

To find the probability of marks between 20 and 40, we standardize
the values using the Z-score formula:
 X −µ
Z=
σ
For X = 20:
20 − 30 −10
Z1 = = = −1.6
6.25 6.25
For X = 40:
40 − 30 10
Z2 = = = 1.6
6.25 6.25
Using the Z-table:

P(20 < X < 40) = P(−1.6 < Z < 1.6)

= 2 × Z (1.6) = 2 × 0.4452 = 0.8904

Expected number of students with marks between 20 and 40:

0.8904 × 200 = 178.08 ≈ 178 students

ii) Probability of marks less than 35:

For X = 35:
35 − 30 5
Z= = = 0.8
6.25 6.25
Using the Z-table:

P(X < 35) = P(Z < 0.8) = 0.5 + Z (0.8) = 0.5 + 0.2881 = 0.7881

Expected number of students with marks less than 35:

0.7881 × 200 = 157.62 ≈ 158 students

Problem 2

The weekly wages of workers in a company are normally distributed

with a mean of Rs. 700 and a standard deviation of Rs. 50. Find
the probability that the weekly wage of a randomly chosen worker
is:
(i) Between Rs. 650 and Rs. 750
(i) More than Rs. 750
Solution:
Given:
Mean (µ) = 700
Standard Deviation (σ) = 50
i) Probability of weekly wage between Rs. 650 and Rs. 750:
To find the probability, we first convert the raw wages to Z-scores
using the formula:
X −µ
Z=
σ
For X = 650:
650 − 700 −50
Z1 = = = −1
50 50
For X = 750:
750 − 700 50
Z2 = = =1
50 50
Using the Z-table:

P(650 < X < 750) = P(−1 < Z < 1)

Since the Z-table gives the area to the left of a given Z-value and
the normal distribution is symmetric:

P(−1 < Z < 1) = 2 × P(Z < 1)

P(−1 < Z < 1) = 2 × 0.3413 = 0.6826

Thus, the probability that the weekly wage is between Rs. 650 and
Rs. 750 is 0.6826.

ii) Probability of weekly wage more than Rs. 750:

For X = 750:
750 − 700
Z= =1
50
Using the Z-table:

P(X > 750) = 0.5 − P(Z < 1)

P(X > 750) = 0.5 − 0.3413 = 0.1587

Therefore, the probability that the weekly wage is more than Rs.
750 is 0.1587.
Problem 3

The lifetime of a certain type of electric bulbs of a particular brand

is normally distributed with an average life of 2000 hours and a
standard deviation of 60 hours. If a firm purchases 2500 bulbs, find
the number of bulbs that are likely to last for:
(i) More than 2100 hours
(ii) Less than 1950 hours
(iii) Between 1900 and 2100 hours
Solution:
Given:
Mean (µ) = 2000 hours
Standard Deviation (σ) = 60 hours
Total number of bulbs = 2500
i) Number of bulbs likely to last more than 2100 hours:
To find the probability, we first convert the raw life times to
Z-scores using the formula:
X −µ
Z=
σ
For X = 2100:
2100 − 2000 100
Z= = ≈ 1.67
60 60
Using the Z-table:

P(X > 2100) = P(Z > 1.67)

The Z-table gives the cumulative probability up to 1.67:

P(Z > 1.67) = 0.5 − 0.4525 = 0.0475

The expected number of bulbs lasting more than 2100 hours is:

2500 × 0.0475 = 118.75 ≈ 119 bulbs

ii) Number of bulbs likely to last less than 1950 hours:
For X = 1950:
1950 − 2000 −50
Z= = ≈ −0.83
60 60
Using the Z-table:

P(X < 1950) = P(Z < −0.83)

= 0.5 − 0.2967 = 0.2033

The expected number of bulbs lasting less than 1950 hours is:

2500 × 0.2033 = 508.25 ≈ 508 bulbs

iii) Number of bulbs likely to last between 1900 and 2100
hours:
For X = 1900:
1900 − 2000 −100
Z1 = = ≈ −1.67
60 60
For X = 2100:
2100 − 2000 100
Z2 = = ≈ 1.67
60 60
Using the Z-table:

P(1900 < X < 2100) = P(−1.67 < Z < 1.67)

= 2 × P(0 < Z < 1.67) = 2 × 0.4575 = 0.9050

The expected number of bulbs lasting between 1900 and 2100
hours is:
2500 × 0.9050 = 2262.5 ≈ 2263 bulbs
Problem 4

In a normal distribution, 31% of the items are under 45, and 8% of

the items are over 64. Find the mean and standard deviation of
the distribution.

Solution:
Given:
P(X < 45) = 0.31
P(X > 64) = 0.08
Let the mean be µ and the standard deviation be σ. We need to
find the Z-scores corresponding to these probabilities.
Step 1: Finding Z-scores from the standard normal
distribution table.

Given, P(X < 45) = P(Z < z1 ) = 0.31

=⇒ P(−∞ < Z < 0) − P(0 < Z < z1 ) = 0.31

=⇒ 0.5 − P(0 < Z < z1 ) = 0.31
=⇒ P(0 < Z < z1 ) = 0.5 − 0.31 = 0.19
From the Z-table, z1 ≈ −0.50.

Given, P(X > 64) = P(Z > z2 ) = 0.08

=⇒ 0.5 − P(0 < Z < z2 ) = 0.08

=⇒ P(0 < Z < z2 ) = 0.5 − 0.08 = 0.42

From the Z-table, z2 ≈ 1.41.
Step 2: Setting up equations for X = 45 and X = 64.
45 − µ
z1 = = −0.50
σ
64 − µ
z2 = = 1.41
σ
Step 3: Solving for µ and σ.
From z1 :

−0.50σ = 45 − µ =⇒ µ = 45 + 0.50σ
From z2 :

1.41σ = 64 − µ
Substitute µ = 45 + 0.50σ into the second equation:

1.41σ = 64 − (45 + 0.50σ)

Simplify:

1.41σ + 0.50σ = 64 − 45
1.91σ = 19
19
σ= ≈ 9.95
1.91
Now, find µ:

µ = 45 + 0.50 × 9.95 = 45 + 4.975 ≈ 49.975

Therefore,
Mean (µ) ≈ 50
Standard Deviation (σ) ≈ 9.95
Problem 5

In an examination, 7% of the students scored less than 35% of the

marks, and 89% of the students scored less than 60% of the
marks. Find the mean and standard deviation if the marks are
normally distributed.

Solution:
Given:
P(X < 35) = 0.07
P(X < 60) = 0.89
Let the mean be µ and the standard deviation be σ. We need to
find the Z-scores corresponding to these probabilities.
Step 1: Finding Z-scores from the standard normal
distribution table.

Given, P(X < 35) = P(Z < z1 ) = 0.07

=⇒ P(−∞ < Z < 0) − P(0 < Z < z1 ) = 0.07

=⇒ 0.5 − P(0 < Z < z1 ) = 0.07

=⇒ P(0 < Z < z1 ) = 0.5 − 0.07 = 0.43
From the Z-table, z1 ≈ −1.48.
For P(X < 60) = 0.89: Given, P(X < 60) = P(Z < z1 ) = 0.89

=⇒ P(−∞ < Z < 0) + P(0 < Z < z1 ) = 0.89

=⇒ 0.5 + P(0 < Z < z1 ) = 0.89

=⇒ P(0 < Z < z1 ) = 0.89 − 0.5 = 0.39
From the Z-table, z2 ≈ 1.23.
Step 2: Setting up equations for X = 35 and X = 60.
35 − µ
z1 = = −1.48
σ
60 − µ
z2 = = 1.23
σ
Step 3: Solving for µ and σ.
From z1 :

−1.48σ = 35 − µ =⇒ µ = 35 + 1.48σ
From z2 :

1.23σ = 60 − µ
Substitute µ = 35 + 1.48σ into the second equation:

1.23σ = 60 − (35 + 1.48σ)

Simplify:

1.23σ + 1.48σ = 60 − 35
2.71σ = 25
25
σ= ≈ 9.23
2.71
Now, find µ:

µ = 35 + 1.48 × 9.23 = 35 + 13.66 ≈ 48.66

Therefore,
Mean (µ) ≈ 48.66
Standard Deviation (σ) ≈ 9.23
Assignment Problems
1. The marks of 1000 students in an examination follows
normal distribution with mean 70 and standard deviation 5.
Find the number students whose marks will be:
(i) Less than 65 [Ans: 159]
(ii) More than 75 [Ans: 59]
(iii) Between 65 and 75 [Ans: 683]
[Given Z (1) = 0.3413]
2. In a test on 2000 electric bulbs, it was found that the life
of a particular make was normally distributed with an
average life of 2040 hours and SD of 60 hours. Estimate the
number of bulbs likely to burn for:
(i) More than 2150 hours [Ans: 67]
(ii) Less than 1950 hours [Ans: 137]
(iii) Between 1920 and 2160 hours [Ans: 1909]
3. In a normal distribution, 7% of items are under 35 and
89% of the items are under 63. Find the mean and standard
deviation of the distribution.
Answer: Mean = 50.29, S.D = 10.33
 Topic 5: Exponential Distribution

Dr. P. Rajendra, Professor, Department of Mathematics,

CMRIT, Bengaluru.
Introduction to Exponential Distribution

(i) The Exponential Distribution is a continuous probability

distribution that is used to model the time between events in
a Poisson process.
(ii) It is characterized by a single parameter α, which represents
the rate at which events occur.
(iii) The Exponential Distribution is memoryless, meaning that the
probability of an event occurring in the future is independent
of how much time has already passed.

Example
The Exponential Distribution can model the time between user
clicks on a webpage or the time between requests to a server.
Probability Density Function (PDF)

▶ The probability density function (PDF) of the Exponential

Distribution is given by:

f (x; α) = αe −αx for x ≥ 0

▶ Here:
(i) x is the random variable representing the time between events.
(ii) α is the rate parameter (the inverse of the mean time between
events).
(iii) e is the base of the natural logarithm (approximately 2.71828).
▶ The PDF describes the likelihood of an event occurring after a
certain amount of time has passed.
Mean and Variance

▶ The Mean (expected value) of the Exponential Distribution is

given by:
1
E [X ] =
α
▶ The Variance of the Exponential Distribution is:

1
Var(X ) =
α2
▶ These properties show that the mean time between events is
the reciprocal of the rate parameter α.

Example
If the average time between failures in a system is 2 hours, the
mean is 2 hours, and the variance is 4 hours squared. The rate
parameter α would be 1/2 = 0.5 failures per hour.
Applications in AI and Data Science

▶ Survival Analysis: The Exponential Distribution is used in

survival analysis to model the time until an event, such as
system failure or churn in customer retention models.
▶ Queueing Theory: The Exponential Distribution is used to
model the time between arrivals in a queue, such as jobs
arriving at a server or customers arriving at a service point.
▶ Network Traffic Modeling: In network security, the
Exponential Distribution can model the time between
detected attacks or anomalies.
▶ Machine Learning Algorithms: Some algorithms assume
that the time between events follows an Exponential
Distribution, especially in reinforcement learning and
predictive maintenance models.
Problem 1

If X is an exponential variant with mean 3, then find P(X > 1)

and P(X < 3).

Solution:

The probability density function (pdf) of an exponential

distribution with mean µ = 3 is given by:
1 −x/µ
f (x) = e , x ≥0
µ
For mean µ = 3, the pdf becomes:
1
f (x) = e −x/3
3
To find P(X > 1):
Z ∞
1 −x/3
P(X > 1) = e dx
1 3
Calculating the integral:
h i∞  
P(X > 1) = −e −x/3 = 0 − −e −1/3 = e −1/3
1

Thus,
P(X > 1) = e −1/3 ≈ 0.7165
To find P(X < 3):
Z 3
1 −x/3
P(X < 3) = e dx
0 3

Calculating the integral:

h i3
P(X < 3) = −e −x/3 = −e −1 − (−1)


0

Thus,
P(X < 3) = 1 − e −1 ≈ 0.6321
Problem 2

The life of a TV tube manufactured by a company is known to

have a mean of 200 months. Assuming that the life of the tube
follows an exponential distribution, find the probability that the life
of a tube manufactured by the company is:
(i) Less than 200 months
(ii) Between 100 and 300 months
(iii) More than 200 months

Solution:

The probability density function (pdf) of an exponential

distribution with mean µ = 200 months is given by:
1 −x/µ
f (x) = e , x ≥0
µ
For mean µ = 200, the pdf becomes:
1 −x/200
f (x) = e
200
(i). Probability that the life is less than 200 months:
Z 200
1 −x/200
P(X < 200) = e dx
0 200
Calculating the integral:
h i200
P(X < 200) = −e −x/200 = −e −1 − (−1)


0

Thus,
P(X < 200) = 1 − e −1 ≈ 0.6321
(ii). Probability that the life is between 100 and 300 months:
Z 300
1 −x/200
P(100 < X < 300) = e dx
100 200
Calculating the integral:
h i300
P(100 < X < 300) = −e −x/200 = −e −1.5 − −e −0.5



100
Thus,
P(100 < X < 300) = e −0.5 − e −1.5 ≈ 0.3033
(iii). Probability that the life is more than 200 months:
Z ∞
1 −x/200
P(X > 200) = e dx
200 200
Calculating the integral:
h i∞
P(X > 200) = −e −x/200 = 0 − −e −1 = e −1


200
Thus,
P(X > 200) = e −1 ≈ 0.3679
Problem 3
The length of a telephone conversation is an exponential random
variable with a mean of 3 minutes. Find the probability that a call:
(i) Ends in less than 3 minutes
(ii) Ends between 3 and 5 minutes
(iii) Ends in more than 4 minutes

Solution:
The probability density function (pdf) of an exponential
distribution with mean µ = 3 minutes is given by:
1 −x/µ
f (x) = e , x ≥0
µ
For mean µ = 3, the pdf becomes:
1
f (x) = e −x/3
3
(i). Probability that the call ends in less than 3 minutes:
Z 3
1 −x/3
P(X < 3) = e dx
0 3
Calculating the integral:
h i3
P(X < 3) = −e −x/3 = −e −1 − (−1)


0

Thus,
P(X < 3) = 1 − e −1 ≈ 0.6321
(ii). Probability that the call ends between 3 and 5 minutes:
Z 5
1 −x/3
P(3 < X < 5) = e dx
3 3
Calculating the integral:
h i5  
P(3 < X < 5) = −e −x/3 = −e −5/3 − −e −1


3

Thus,
P(3 < X < 5) = e −1 − e −5/3 ≈ 0.0996
(iii). Probability that the call ends in more than 4 minutes:
Z ∞
1 −x/3
P(X > 4) = e dx
4 3
Calculating the integral:
h i∞  
P(X > 4) = −e −x/3 = 0 − −e −4/3
4

Thus,
P(X > 4) = e −4/3 ≈ 0.2636
Assignment Problems

1. If X is an exponential variant with mean 4, then find

(i) P(0 < x < 1) [Ans: 1 − e −1/4 ]
(ii) P(x > 2) [Ans: e −1/2 ]
(iii) P(−∞ < x < 10) [Ans:1 − e −5/2 ]

2. In a certain town, the duration of a shower has a mean of 5

minutes. What is the probability that the shower will last for:
(i) 10 minutes and more [Ans: e12 ]
(ii) Less than 10 minutes [Ans: 1 − e12 ]
1 1
(iii) Between 10 and 12 minutes [Ans: e 12/5 − e2 ]