Copyright© Dorling Kindersley India Pvt Ltd

Chapter 6
Discrete Probability
Distributions

Business Statistics - Naval Bajpai

Learning Objectives

Copyright© Dorling Kindersley India Pvt Ltd

Upon completion of this chapter, you will be able to:

 Understand the difference between discrete and continuous

distributions
 Understand the concept of mean, variance, and standard
deviation of discrete distribution
 Understand the concept of binomial distribution and solve
problems of binomial distribution
 Understand the concept of Poisson distribution and solve
problems of Poisson distribution
 Understand the concept of hypergeometric distribution and
solve problems of hypergeometric distribution
 Decide when Poisson distribution can be a reasonable
approximation of the binomial distribution

􀂄 Business Statistics - Naval

Bajpai
Difference Between Discrete and Continuous

Copyright© Dorling Kindersley India Pvt Ltd

Random Distribution

 A random variable is a variable which contains the

outcome of a chance experiment.
 A random variable that assumes either a finite number of
values or a countable infinite number of possible values is
termed as a discrete random variable.
 A random variable that assumes any numerical value in an
interval or can take values at every point in a given interval
is called a continuous random variable.
 The outcomes of a random variable and the probabilities
attached to these can be arranged in distributions. These
distributions can be broadly classified into discrete and
continuous distributions.

Business Statistics - Naval

Bajpai
Discrete Probability Distribution

Copyright© Dorling Kindersley India Pvt Ltd

Probability distribution for a random variable specifies
how probabilities are distributed over the random variable.

Alpha Motors Example

Alpha Motors is the dealer of a leading car company in
Gujarat. It conducted an analysis of sales in the past 200
days for opening a new showroom in another locality. Data
collected on the number of cars sold in the past 200 days
revealed that there were 25 days with zero cars sold, 50
days with one car sold, 75 days with two cars sold, 20 days
with three cars sold, and 30 days with four cars sold. Now
consider an experiment of selecting a day in the operations
of Alpha Motors.

Business Statistics - Naval

Bajpai
Alpha Motors Example (Contd.)

Copyright© Dorling Kindersley India Pvt Ltd

Figure 6.1 : Graphical representation of probability
distribution of number of cars sold during a day

Business Statistics - Naval

Bajpai
Mean or Expected Value

Copyright© Dorling Kindersley India Pvt Ltd

 If a process is repeated over a long
period of time, then the average
of the outcomes is most likely to
approach a long-run expected
value or mean value.
 Mean or expected value of a
discrete distribution
 To compute the expected value
or the average value of a
discrete random variable, we
multiply each value of the random
variable x by the corresponding
probability P(x) and then add the
resulting product.

Business Statistics - Naval

Bajpai
Variance of a Discrete Distribution

Copyright© Dorling Kindersley India Pvt Ltd

Variance of a discrete distribution is given by:

Solved Examples\Excel\expected value (Alpha motors).xls

Solved Examples\Excel\variance (Alpha motors).xls

Business Statistics - Naval

Bajpai
Binomial Distribution

Copyright© Dorling Kindersley India Pvt Ltd

Binomial distribution describes discrete data resulting from
an experiment known as the Bernoulli process. Tossing
of a fair coin for a fixed number of times is a Bernoulli
process and the outcomes of such tosses can be
represented by binomial distribution.

Assumptions of Binomial Distribution

 The experiment involves a sequence of n identical
trials.
 For each trial there can be two possible outcomes. One is
referred to as success and the other as failure.
 The trials are independent in nature.
 The probability of success p and the probability of failure
q = (1 – p) remain constant throughout the experiment.

Business Statistics - Naval

Bajpai
Solving the Problem Using Binomial Formula

Copyright© Dorling Kindersley India Pvt Ltd

Example 6.1: Consider a fair coin tossing experiment.
What is the probability of getting two heads in three trials?

Solved Examples\Excel\Ex 6.1.xls

Solved Examples\Minitab\Ex 6.1.MPJ

Business Statistics - Naval

Bajpai
 Copyright© Dorling Kindersley India Pvt Ltd
Example 6.2: A manufacturing company of south Maharashtra found
that after launching a golden handshake scheme for voluntary
retirement, 10% of workers are unemployed. What is the probability
of obtaining three or fewer unemployed workers in a random sample
of 30 in a survey conducted by the company?

We have to find out the probability of getting (a) zero unemployed, x = 0;

(b) one unemployed, x = 1; (c) two unemployed x = 2; and (d) three
unemployed, x = 3 workers.

Business Statistics - Naval

Bajpai
 Copyright© Dorling Kindersley India Pvt Ltd
 Solved Examples\Excel\Ex 6.2(individual prob
computation).xls
 Solved Examples\Excel\Ex 6.2(cumulative prob
computation).xls
 Solved Examples\Minitab\Ex 6.2.MPJ

Business Statistics - Naval

Bajpai
Mean and Variance of a Binomial Probability

Copyright© Dorling Kindersley India Pvt Ltd

Distribution

Business Statistics - Naval

Bajpai
Graphical Presentation of the Binomial

Copyright© Dorling Kindersley India Pvt Ltd

Probability Distribution
 Solved Examples\Excel\graphical presentation of binomial
distribution.xls

 Solved Examples\Minitab\binomial probablities (graphical

presentation).MPJ

Business Statistics - Naval

Bajpai
Poisson Distribution

Copyright© Dorling Kindersley India Pvt Ltd

 For a given number of trials, the binomial distribution
describes a distribution of two possible outcomes: either success
or failure. The Poisson distribution focuses on the number of
discrete occurrences over an interval.
 Poisson formula is also referred to as the Law of Improbable
Events. This is related to the fact that the Poisson distribution
describes the occurrence of rare events.
Properties of Poisson distribution
 Each occurrence of an event is independent of the occurrence
of the other event.
 The probability of an occurrence is the same for any two
intervals of equal length.
 Poisson distribution describes discrete occurrences over a
specific time interval.
 The expected number of occurrences must hold constant for all
the time intervals of the same size.
 In each interval, occurrences can range from zero to infinity.

Business Statistics - Naval

Bajpai
Poission Distribution (Contd.)

Copyright© Dorling Kindersley India Pvt Ltd

 For a Poisson distribution, over a long period of time, a
long run average can be determined. This long run average is
generally denoted by the Greek letter lambda
 Poisson formula is given as:

Example 6.3: A research firm is investigating the safety of a

dangerous road intersection. Historical data (from past police
records) indicates an average of 6 accidents per month at this
particular intersection. The number of accidents are distributed
according to a Poisson distribution. The research firm wants to
calculate the probability of exactly 0, 1, 2, 3, 4, or 5 accidents
in any month.

Business Statistics - Naval

Bajpai
Solution (Example 6.3)

Copyright© Dorling Kindersley India Pvt Ltd

Business Statistics - Naval
Bajpai
 Copyright© Dorling Kindersley India Pvt Ltd
Example 6.4: From Example 6.3, calculate the probability of
three or fewer accidents.

Solved Examples\Excel\Ex 6.3 & 6.4.xls

Solved Examples\Minitab\Ex 6.3 & 6.4.MPJ

Business Statistics - Naval

Bajpai
Graphical Presentation of the Poisson
Probability Distribution

Copyright© Dorling Kindersley India Pvt Ltd

 Solved Examples\Excel\graphical presentation of poisson
distribution.xls

 Solved Examples\Minitab\Poisson probabilities (graphical

presentation).MPJ

Business Statistics - Naval

Bajpai
 Poisson Probability Distribution as an Approximation of

Copyright© Dorling Kindersley India Pvt Ltd

the Binomial Probability Distribution

 Binomial problems with large n

and a small value of p, that
is, when the number of trials is
large but the binomial
probability of success is small,
can be approximated using the
Poisson distribution.
 Statisticians most often use n
larger than or equal to 20 and
p less than or equal to 0.05 as
the right case of approximating
binomial problems by the
Poisson distribution.

Business Statistics - Naval

Bajpai
 Copyright© Dorling Kindersley India Pvt Ltd
Example 6.5: A manufacturing firm has 30 machines. The
probability that any one of them will not function during a day
is 0.01. What is the probability that exactly two machines will
be out of order on the same day?

Solved Examples\Excel\Ex 6.5.xls

Business Statistics - Naval

Bajpai
Hypergeometric Distribution

Copyright© Dorling Kindersley India Pvt Ltd

 Hypergeometric probability distribution is related to binomial
distribution, and often used by statisticians as a complement to
binomial distribution.

 There are two main differences between binomial distribution and

hypergeometric distribution. First, the trials are not
independent, and second, the probability of success
changes from trial to trial.

 Hypergeometric distribution also consists of two possible outcomes:

success and failure. To apply Hypergeometric distribution, the
user should be aware of the population size and proportion of
success and failure in the population. In hypergeometric
distribution, sampling is done without replacement so
information about the population is important to determine the
probability of success in each successive trial as the probability
changes in each successive trial.

Business Statistics - Naval

Bajpai
Characteristics of a Hypergeometric Distribution:

Copyright© Dorling Kindersley India Pvt Ltd

 There can be two possible outcomes for each trial.
 It is a discrete distribution.
 Sampling is done without replacement in a
hypergeometric distribution.
 Population N is finite and known.
 The number of successes in the population r is known.

Business Statistics - Naval

Bajpai
 Copyright© Dorling Kindersley India Pvt Ltd
Example 6.6: A consumer electronics company has 24 showrooms
located across India. Out of these 24 showrooms, 12 are located in
Gujarat. If five showrooms are selected at random from the entire
list, what is the probability that one or more randomly selected
showrooms are located in Gujarat?

Solved Examples\Excel\Ex 6.6.xls

Solved Examples\Minitab\Ex 6.6.MPJ

Business Statistics - Naval

Bajpai