Probability

Chapter 5
COMMONLY USED
DISCRETE DISTRIBUTIONS
1. The Bernoulli and The Binomial Distribution
2. The Hypergeometric Distribution
3. The Poisson Distribution
4. The Geometric Distribution
5. The Negative Binomial Distribution
6. The Discrete Uniform Distribution

1st Semester 2022

 A first course in Probability

1. The Bernoulli and Binomial distributions

The Bernoulli Random Variable
• Assume you have an experiment which can be classified as either success
or failure.
• If you associate a random variable 𝑋 such that 𝑋 = 1 corresponds to a
success and 𝑋 = 0 corresponds to a failure then
 P (X = 1) = 𝑝 (1) = 𝑝
 P (X = 0) = 𝑝 (0) = 1 − 𝑝
• Such a random variable is a called a Bernoulli random variable.
• We have
𝐸 (𝑋) = 𝑝 and 𝑉𝑎𝑟 𝑋 = 𝑝 (1 − 𝑝)

1st Semester 2020

 Probability

1. The Bernoulli and Binomial distributions

The Binomial Random Variable
• Consider a sequence of 𝑛 independent success/failure experiments,
each of which yields success with probability 𝑝.
• Let 𝑋 denote the number of successes then we have
𝑋 = 𝑋1 + 𝑋2 + … + 𝑋𝑛
where 𝑋𝑖 is a Bernoulli random variable with probability 𝑝. Then 𝑋 is a
binomial random variable of parameters (𝑛, 𝑝) .

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

• 𝑋 is a discrete random variable in {0, 1, … , 𝑛} such that
𝑛 𝑘
𝑃(𝑋 = 𝑘) = 𝑝 1 − 𝑝 𝑛−𝑘 (0≤𝑘≤𝑛)
𝑘

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

Example 5.1: Let 𝑋 be the number of heads in 3 tosses of a fair coin.
Find the probability that there are 2 heads.

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

Example 5.2: A student takes a multiple choice examination with 10
questions. He has not attended class or studied for three weeks and
plans to guess on each question by having his calculator display a
random integer from 1 to 5 (There are 5 choices for each question).
Find the probability that the student gets at least 2 questions right.

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

Example 5.3: Everyday one of your classmates is taking the tram twice
without any ticket. There is a 5% chance of meeting inspectors each
time one boards the tram. What is the probability that he is going to be
caught at least twice in a 30 day month?

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

Example 5.4: Your friend pretends that he is able to distinguish pepsi
from coke. You give him a test. Out of 5 trials, he gets the right answer
4 times. What is the probability that he just got lucky?

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

Example 5.5: A survey from Teenage Research Unlimited found that
30% of teenage consumers receive their spending money from part-
time jobs. If 5 teenagers are selected at random, find the probability
that at least three of them will have part-time jobs.

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

Example 5.6: (Insurance) The 1979-81 United States Life Table given in
Bowers et al. gives the probability of death within one year for a 57-
year-old person as 0.01059. Suppose that you are an insurance agent
with 10 clients who have just reached age 57. You are willing to assume
that deaths of the clients are independent events.
(a) What is the probability that all 10 survive the next year?
(b) What is the probability that 9 will survive and exactly one will die
during the next year?

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

• If 𝑋 is a binomial random variable with parameters 𝑛 and 𝑝, then
𝐸(𝑋) = 𝑛𝑝
𝑉𝑎𝑟(𝑋) = 𝑛𝑝(1 − 𝑝)

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

Example 5.7: Let 𝑋 be the number of correct answers for a student
guessing on a 10 question multiple choice test with 5 choices on each
question. Find 𝐸(𝑋) and 𝑉𝑎𝑟(𝑋).

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

Properties
If 𝑋 is a binomial random variable with parameters (𝑛, 𝑝), 0 < 𝑝 < 1,
then as 𝑘 goes from 0 to 𝑛, 𝑃{𝑋 = 𝑘} first increases monotonically
and then decreases monotonically, reaching its largest value when 𝑘 is
the largest integer less than or equal to (𝑛 + 1)𝑝.

1st Semester 2022

 Probability

1. The Bernoulli and Binomial distributions

Computing the Binomial Distribution Function
𝑖 𝑛 𝑘 𝑛−𝑘
P(X ≤ i) = 𝑘=0 𝑝 1−𝑝
𝑘

𝑝 𝑛−𝑘
𝑃 𝑋 = 𝑘 + 1 = 𝑃(𝑋 = 𝑘)
1−𝑝 𝑘+1

1st Semester 2022

 Probability

2. The Hypergeometric Distributions

Consider a barrel or urn containing 𝑁 balls of which 𝑚 are white and
𝑁 − 𝑚 are black. We take a simple random sample (i.e. without
replacement) of size 𝑛 and measure 𝑋, the number of white balls in the
sample.
The Hypergeometric distribution is the distribution of 𝑋 under this
sampling scheme and
𝑚 𝑁 −𝑚
𝑖 𝑛 − 𝑖
𝑃 𝑋=𝑖 =
𝑁
𝑛

1st Semester 2022

 Probability

2. The Hypergeometric Distributions

Example 5.8: Suppose that as part of a survey, 7 houses are sampled at
random from a street of 40 houses in which 5 contain families whose
family income puts them below the poverty line. What is the
probability that:
(a) None of the 5 families are sampled?
(b) 4 of them are sampled?
(c) No more than 2 are sampled?
(d) At least 3 are sampled?

1st Semester 2022

 Probability

2. The Hypergeometric Distributions

Let us introduce 𝑝 = 𝑚/𝑁 then
𝐸 𝑋 = 𝑛𝑝
𝑁−𝑛
𝑉𝑎𝑟 𝑋 = 𝑛𝑝(1 − 𝑝)
𝑁−1

1st Semester 2022

 Probability

2. The Hypergeometric Distributions

• Suppose that 𝑚 is very large compared to n, it seems reasonable that
sampling without replacement is not too much different than
sampling with replacement. It can indeed be shown that the
hypergeometric distribution can be well approximated by the
binomial of parameters 𝑝 = 𝑚/𝑁 and 𝑁.

1st Semester 2022

 Probability

2. The Hypergeometric Distributions

We are interested in estimating the population 𝑁 of animals inhabiting a certain
region. To achieve this, capture-recapture studies proceed as follows. First, you
capture 𝑚 individuals, mark them and release them in the nature. A few days later,
you capture say 𝑛 animals; among the 𝑛 animals some of them are marked and some
are not. Let 𝑋 be the number of animals which have been recaptured, then 𝑋 follows
an hypergeometric distribution of parameters 𝑁, 𝑚 and 𝑛.
Assume you have recaptured 𝑋 = 𝑥 animals, then you can estimate 𝑁 by maximizing
with respect to 𝑁 the probability
𝑚 𝑁 −𝑚
𝑥 𝑛−𝑥
𝑃 𝑋=𝑥 =
𝑁
𝑛
This known as the Maximum Likelihood (ML) estimate of 𝑁.
One can show that the ML estimate is the largest integer value not exceeding 𝑚𝑛/𝑥

1st Semester 2022

 Probability

2. The Hypergeometric Distributions

Example 5.9: Suppose that we have a lake containing 𝑁 fishes where 𝑁
is unknown.
We capture and mark 𝑚 = 100 fishes. A few days later, we capture
𝑛 = 50 fishes, 𝑋 of them are marked. What is the ML estimate of N
if 𝑋 = 35 and 𝑋 = 5?

1st Semester 2022

 Probability

3. Poisson Distribution
• A discrete random variable 𝑋 taking values 0, 1, 2, … is said to be a
Poisson random variable with parameter λ (λ>0) if
λ𝑘.𝑒 −λ
𝑃 𝑋 = 𝑘 = (𝑘 = 0; 1; 2 … )
𝑘!
• This expresses the probability of a number of events occurring in a
fixed period of time if these events occur with a known average
rate λ.

1st Semester 2022

 Probability

3. Poisson Distribution
If we consider a binomial random variable 𝑋 of parameters (𝑛, 𝑝) such
that 𝑛 is large and 𝑝 is small enough so that 𝑛𝑝 is moderate then the
binomial distribution can be well-approximated by the Poisson
distribution of parameter λ = 𝑛𝑝.

1st Semester 2022

 Probability

3. Poisson Distribution
Some examples of random variables that generally obey the Poisson
probability law are as follows:
• The number of misprints on a page (or a group of pages) of a book
• The number of people in a community who survive to age 100
• The number of wrong telephone numbers that are dialed in a day
• The number of packages of dog biscuits sold in a particular store each
day
• The number of customers entering a post office on a given day
• The number of vacancies occurring during a year in the federal
judicial system

1st Semester 2022

 Probability

3. Poisson Distribution
• The number of a-particles discharged in a fixed period of time from
some radioactive material
• The number of earthquakes occurring during some fixed time span
• The number of wars per year
• The number of electrons emitted from a heated cathode during a
fixed time period
• The number of deaths, in a given period of time, of the policyholders
of a life insurance company

1st Semester 2022

 Probability

3. Poisson Distribution
If 𝑋 is a Poisson random variable with parameter λ, then
𝐸(𝑋) = 𝑣𝑎𝑟(𝑋) = λ

1st Semester 2022

 Probability

3. Poisson Distribution
Example 5.10: There are 50 misprints in a book which has 250 pages
and assume these errors follow a Poisson distribution of parameter
λ = 50/250 = 0.2. Find the probability that page 100 has no
misprints. Find the probability that page 100 has 2 misprints.

1st Semester 2022

 Probability

3. Poisson Distribution
Example 5.11: During the noon lunch hour, 47 customers will walk
through the door of the post office. Assume that each person arrives at
a random time, independent of the other customers. What is the
probability that more than one person walks through the door during
the first minute?

1st Semester 2022

 Probability

3. Poisson Distribution
Example 5.12: Each year the London Metropolitan Police record around
160 murders, and this has been stable for the last 5 years. Each of
these murders is an individual crime that cannot be predicted. It may
appear strange, but this very randomness means that the overall
pattern of murders is in some ways quite predictable.
Assuming the number of murders are Poisson distributed, compute the
probability of having no murder during a day, 3 or more murders in one
day, a week without any murder.

1st Semester 2022

 Probability

3. Poisson Distribution
Example 5.13: Brain cancer is a rare disease. In any year there are
about 3.1 cases per 100000 of population (US figure from TIME).
Suppose a small medical insurance company has 150000 people on
their books. How many claims stemming from brain cancer should the
company expect in any year? What is the probability of getting more
than 2 claims related to brain cancer in a year?

1st Semester 2022

 Probability

3. Poisson Distribution
Computing the Poisson Distribution Function

𝑃(𝑋 = 𝑖 + 1) λ
=
𝑃(𝑋 = 𝑖) 𝑖+1

1st Semester 2022

 Probability

4. The Geometric Distribution

Consider yet again independent trials, each with success probability 𝑝. These
trials are performed until a success occurs.
Let 𝑋 the number of trials required then 𝑋𝜖{1, 2, … } then it follows a
geometric probability mass function

𝑃 𝑋 = 𝑘 = (1 − 𝑝)𝑘−1 𝑝

We have
1
𝐸 𝑋 =
𝑝
1−𝑝
𝑉𝑎𝑟(𝑋) =
𝑝2

1st Semester 2022

 Probability

4. The Geometric Distribution

Example 5.14: A telemarketer makes repeated calls to persons on a
computer generated list. The probability of making a sale on any
individual call is 𝑝 = 0.10. Successive calls are independent. Let 𝑋 be
the number of trials to obtain the first sale. Find
(a) 𝑃(𝑋 = 2)
(b) 𝑃(𝑋 > 2)
(c) 𝐸(𝑋), 𝑉𝑎𝑟(𝑋)
(d) The calls cost $0.50 each. What is the expected cost of obtaining
the first success.

1st Semester 2022

 Probability

5. The Negative Binomial Random Variable

• Suppose that independent trials, each having probability 𝑝, 0 < 𝑝 < 1,
of being a success are performed until a total of 𝑟 successes is
accumulated. If we let 𝑋 equal the number of trials required, then
𝑘−1
𝑃 𝑋=𝑘 = 1 − 𝑝 𝑘−𝑟 𝑝𝑟 , 𝑘 = 𝑟, 𝑟 + 1 …
𝑟−1
• Any random variable 𝑋 whose probability mass function is given by the
above equation is said to be a negative binomial random variable with
parameters (𝑟, 𝑝).
• Note that a geometric random variable is just a negative binomial with
parameter (1, 𝑝).

1st Semester 2022

 Probability

5. The Negative Binomial Random Variable

If 𝑋 is a negative binomial random variable with parameters
(𝑟, 𝑝 ) then we have

𝑟
𝐸 𝑋 =
𝑝
𝑟(1−𝑝)
𝑉𝑎𝑟 𝑋 =
𝑝2

1st Semester 2022

 Probability

5. The Negative Binomial Random Variable

Example 5.15: You are playing the slot machine on which the
probability of a win on any individual trial is 0.05. You will play until you
win twice. What is the probability that you will lose exactly 4 times
before the second win?

1st Semester 2022

 Probability

5. The Negative Binomial Random Variable

Example 5.16: Find the expected value and the variance of the number
of times one must throw a die until the outcome 1 has occurred 4
times.

1st Semester 2022

 Probability

6. The Discrete Uniform Distribution

Discrete Uniform Distribution on 1, 2, … , 𝑛
1
𝑝 𝑥 = , 𝑥 = 1, 2, … , 𝑛
𝑛

𝑛+1
𝐸 𝑋 =
2

𝑛2 −1
𝑉𝑎𝑟 𝑋 =
12

1st Semester 2022

 Probability

6. The Discrete Uniform Distribution

Example 5.17: Let 𝑋 be the number that appears when a single fair die
is rolled. Find 𝐸(𝑋), 𝑉𝑎𝑟(𝑋)

1st Semester 2022

 Probability

6. The Discrete Uniform Distribution

Example 5.18: A contestant on a game show selects a ball from an um
containing 25 balls numbered from 1 to 25. His prize is $1,000 times
the number of the ball selected. If 𝑋 is the random variable for the
amount he wins, find the mean and standard deviation of 𝑋.

1st Semester 2022

 Probability

Chapter 5 - Exercises
Exercise 1: A student takes a 10 question true-false test. He has not
attended class nor studied the material, and so he guesses on every
question. What is the probability that he gets
(a) exactly 5 questions correct;
(b) he gets 8 or more correct?

1st Semester 2022

 Probability

Chapter 5 - Exercises
Exercise 2: The United States Senate has 100 members. Suppose there
54 Republicans and 46 Democrats.
(a) If a committee of 15 is selected at random, what is expected
number of Republicans on this committee?
(b) What is the variance of the number of Republicans?

1st Semester 2022

 Probability

Chapter 5 - Exercises
Exercise 3: An insurance company has 5,000 policyholders who have
had policies for at least 10 years. Over this period there have been a
total of 12,200 claims on these policies. Assuming a Poisson
distribution for these claims, answer each of the following.
(a) What is the average number of claims per policy per year?
(b) What is the probability that a policyholder will file less than 2 claims
in a year?
(c) If all claims are for $1,000, what is the mean claim amount for a
policyholder in a year?

1st Semester 2022

 Probability

Chapter 5 - Exercises
Exercise 4: If you roll a pair of fair dice, the probability of getting an 11
is 1/18. If you roll the dice repeatedly, what is the probability that the
first 11 occurs on the eighth roll?

1st Semester 2022

 Probability

Chapter 5 - Exercises
Exercise 5: A single fair die is rolled repeatedly.
(a) What is the probability that the fourth six appears on the twentieth
roll?
(b) What is the mean number of total rolls needed to get 4 sixes?

1st Semester 2022

 Probability

Chapter 5 - Exercises
Exercise 6: A telemarketer makes successful calls with probability 0.20.
What is the probability that her fifth sale will be on her sixteenth call?

1st Semester 2022

Chapter 5 - Exercises
Exercise 7: A contestent on a game show selects a ball from an um
containing 25 balls numbered from I to 25. His prize is $1,000 times the
number of the ball selected. If X is the random variable for the
amount he wins, find the mean and standard deviation of X