Discrete Probability Distributions

Binomial Distribution:
Binomial distribution is used to model an experiment that confirms the following list
requirements:
➢ The experiment has a sequence of n independent Bernoulli trials.
➢ Each trial has only two possible outcomes which are either success or failure.
➢ The trials are independent.
➢ Each trial has the same probability of success, p and probability of failure, 𝑞 = 1 – 𝑝.

Let,
𝑋 = number of success in n trials
Then, 𝑋 is a binomial random variable with distribution function (pmf),
𝑛
𝑝(𝑥) = 𝐶𝑥 𝑝 𝑥 (1 − 𝑝)𝑛−𝑥 ; 𝑥 = 0, 1, 2, … , 𝑛
𝑛!
= 𝑝 𝑥 (1 − 𝑝)𝑛−𝑥
(𝑛 − 𝑥)! 𝑥!

Here, n! = n(n-1) (n-2) …1 0! = 1, 1! = 1, 2! = 2*1 = 2, 3! = 3*2*1= 6

Thus, we can write it as, 𝑋 ~ 𝑏𝑖𝑛𝑜𝑚𝑖𝑎𝑙 (𝑛, 𝑝)

Mean of the binomial distribution, 𝜇 = 𝐸(𝑋) = ∑𝑥 𝑝(𝑥) = 𝑛𝑝

Variance of binomial distribution, 𝜎 2 = 𝑉𝑎𝑟(𝑋)
=𝐸(𝑋 2 ) − 𝜇 2
= 𝑛𝑝(1 − 𝑝)
= 𝑛𝑝𝑞

Standard deviation of binomial distribution, 𝜎 = √𝑛𝑝𝑞

Summer2024_MDG_STA201
 Geometric Distribution:
The geometric distribution represents the number of failures before getting a success in a series
of Bernoulli trials.

➢ Suppose that independent Bernoulli trials each having probability 𝑝 of success are
performed until a success occurs.

➢ Let, 𝑋 = No. of trails required to get the first success.

Then we can write,

𝑋 ~ geometric (𝑝) with probability mass function (pmf),

P (𝑋=𝑥) = (1 − 𝑝)𝑥−1 𝑝 ; 𝑥 = 1, 2, 3, …

❖ Assumptions for the geometric distribution:

➢ Each trial has only two possible outcomes which are success and failure

➢ The trials are independent

➢ The probability of success is the same for each trial.

Mean of the geometric distribution, 𝜇 = 𝐸(𝑋) = 1/𝑝

1− 𝑝
Variance of the geometric distribution, 𝜎 2 = 𝑉𝑎𝑟(𝑋) = 𝑝2

Example 1:

A fair die is thrown until a “6” occurs.

i) What is the probability that at most 3 tosses will be required?

ii) What will be the average no. of tosses required?

Summer2024_MDG_STA201
Solution:
1
Here, the probability of occurring “6” is, 𝑝 = 6

𝑋 = number of trials required to get a “6”

1
Thus, 𝑋 ~ geometric (𝑝 = 6)

i) The probability that at most 3 tosses will be required,

P (𝑋 ≤ 3) = P (𝑋 = 1) + P (𝑋 =2) + P (𝑋 = 3)
5 1 5 1 5 1
= (6)0 ∗ (6) + (6) ∗ (6) + (6)2 ∗ (6)

1 5 25
= + +
6 36 216
36+30+25
=
216
91
=
216

= 0.42

ii) The average number of tosses required is,

µ = E (𝑋) = 1/𝑝
1
= 1
6

=6
❖ The geometric distribution is useful for determining the likelihood of a success given a
limited number of trials, which is highly applicable to the real world in which unlimited (and
unrestricted) trials are rare. Some of the practical examples of geometric distributions are
given below:

➢ In sports, particularly in baseball, a geometric distribution is useful in analyzing the

probability a batter earns a hit before he receives three strikes; here, the goal is to reach a
success within 3 trials.

Summer2024_MDG_STA201
 ➢ In cost-benefit analyses, such as a company deciding whether to fund research trials that,
if successful, will earn the company some estimated profit, the goal is to reach a success
before the cost outweighs the potential gain.

➢ In time management, the goal is to complete a task before some set amount of time.

Poisson Distribution

The Poisson distribution is used to model a discrete random variable representing the number of
occurrences of some random events in an interval of time or space (or some volume of matter).
The possible values of 𝑋 = 𝑥 are:

𝑥 = 0, 1, 2, 3, …

Let,

𝑋 = A random variable usually counts or number of occurrences

Then, 𝑋 is a Poisson random variable with distribution function (pmf),

𝑒 −𝜆 𝜆𝑥
𝑝(𝑥) = ; 𝑥 = 0, 1, 2, …
𝑥!

We can write it as, 𝑋 ~ 𝑃𝑜𝑖𝑠𝑠𝑜𝑛 (𝜆)

Mean of the Poisson distribution, 𝜇 = 𝐸(𝑋) = ∑𝑥 𝑝(𝑥) = 𝜆

Variance of Poisson distribution, 𝜎 2 = 𝐸(𝑋 2 ) − 𝜇 2 = 𝜆

Standard deviation of Poisson distribution, 𝜎 = √𝜆

* Count data with no upper limit

Summer2024_MDG_STA201
 ❖ Some random quantities that can be modeled by Poisson distribution:

(i) Number of patients in a waiting room in an hour.

(ii) Number of surgeries performed in a month.

(iii)Number of car accidents daily in a city.

(iv) Number of rats in each house in a particular city.

Note:

❖  is the average (mean) of the Poisson distribution.

If 𝑋 = The number of patients seen in the emergency unit in a day, and if

𝑋 ~ Poisson (), then:

❑ The average (mean) of patients seen every day in the emergency unit = .

❑ The average (mean) of patients seen every month in the emergency unit =30.

❑ The average (mean) of patients seen every year in the emergency unit = 365.

❑ The average (mean) of patients seen every hour in the emergency unit = /24.

Also, notice that:

(i) If Y = The number of patients seen every month, then:
Y ~ Poisson (*), where *=30

(ii) W = The number of patients seen every year, then:

Summer2024_MDG_STA201
 W ~ Poisson (*), where *=365

(iii) V = The number of patients seen every hour, then:

V ~ Poisson (*), where *= /24

Example 6:

The average number of errors on a page of a certain magazine is 0.2. What is the probability that
the next page (or a randomly selected page) you read contains-
i. 0 (zero) error?
ii. 2 or more errors?
iii. What is the average error per page?
iv. Also, find standard deviation of the number of errors.

Solution:

Let,
𝑋 = number of errors in a page

Here, λ = average number of errors per page= 0.2

∴ 𝑋 ~ 𝑃𝑜𝑖𝑠𝑠𝑜𝑛 (𝜆 = 0.2)

𝑒 −𝜆 𝜆𝑥 𝑒 −0.2 0.2𝑥
𝑝(𝑥) = ; 𝑥 = 0, 1, 2, … =
𝑥! 𝑥!

e−0.2 0.2x e−0.2 0.20 e−0.2 ∗1

i. P(X = 0) = = = = 0.8187
x! 0! 1

ii. P(X ≥ 2) = 1 − P(X < 2) = 1 − [P(X = 0) + P(X = 1)]

e−0.2 0.20 e−0.2 0.21
= + = 1 − [e−0.2 + e−0.2 ∗ 0.2] = 0.01756
0! 1!

iii. Average number of errors, 𝐸(𝑋) = 𝜆 = 0.2

Summer2024_MDG_STA201
 iv. Standard deviation, 𝑆𝐷(𝑋) = √𝜆 = √0.2 = 0.45

The probabilities for different values of x are given below:

x p(x)
0 0.82
1 0.16
2 0.02
3 0.00
4 0.00
5 0.00
6 0.00
7 0.00
8 0.00
9 0.00
10 0.00
15 0.00
20 0.00
30 0.00
40 0.00
50 0.00
100 0.00

Summer2024_MDG_STA201
 Poisson (λ=0.2)
1.00

0.50

0.00
0 2 4 6 8 10 20 40 100
p(x)

From the above graph and the table, it can be clearly observed that, for only six values of x, the
probabilities are obtained.

Example 7:

Suppose that the number of accidents per day in a city has a Poisson distribution with average 2
accidents.

(1) What is the probability that in a day:

(i) The number of accidents will be 5?

(ii) The number of accidents will be less than 2?

(2) What is the probability that there will be 6 accidents in 2 days?

(3) What is the probability that there will be no accidents in an hour?

Summer2024_MDG_STA201
Solution:

(1) 𝑋 = number of accidents in a day

𝑋 ~ Poisson (2) ( = 2)

(ii) P (𝑋 = 5) = 0.036089

(ii) P (𝑋 <2) =0.406005

(2) 𝑌 = number of accidents in 2 days

𝑌 ~ Poisson (4) (* = 4)

P (𝑌 = 6) = 0.1042

(3) 𝑊 = number of accidents in an hour

𝑊 ~ Poisson (0.083) (** =  /24 = 2/24= 0.083)

P (𝑊 = 0) = 0.920

Summer2024_MDG_STA201