CHAPTER 6:

Discrete Probability
Distributions
Business Mathematics 41
Presented by: John Melvin V. Baranda
 Learning Objectives
 Understand both the concept and the applications of a probability distributio
n for a random variable.
 Determine whether the random variable in a probability distribution is of th
e discrete type or the continuous type.
 Differentiate among the binomial, hypergeometric, and Poisson discrete prob
ability distributions and their applications.
 Understand what is meant by a Bernoulli process and how this applies to the
consecutive trials associated with the binomial distribution.
 Use the appropriate probability distribution in determining the probability t
hat a discrete random variable will have a given value or a value in a given r
ange.
 Random Variables: Discrete versus Continuous

 A random variable is a variable that can take on different values according to the
outcome of an experiment.
 DISCRETE RANDOM VARIABLE - A random variable that can take on only
certain values along an interval, with the possible values having gaps between them.
For example, in a given group of five children, the number who got at least one electronic
toy for Christmas would be 0, 1, 2, 3, 4, or 5. It could not be a number between any of
these values, such as 2.338.
 CONTINUOUS RANDOM VARIABLE A random variable that can take on a value
at any point along an interval.
The exact temperature outside as you’re reading this book could be 13.568, 78.352, or
83.815 degrees Fahrenheit, or any of an infinity of other values in the range of
temperatures where colleges and universities are located. (The temperature examples
have been expressed to just three decimal places here, but there would be countless
possibilities along the temperature continuum.)
 Discrete Probability Distribution
Example 1 An experiment is conducted in which a fair coin is flipped twice. The result of
the experiment will be the random variable x = the number of times that
heads comes up.
Sequence Random Variable X Probability
HH 2 0.25
HT 1 0.25
TH 1 0.25
TT 0 0.25
1.00
x P(x)

Two tosses of a coin: Discrete probability distribution

0 0.25
for the random variable x = number of heads 1 0.50
2 0.25

1.00
 Characteristics of a discrete probability distribution:

1. For any value of x, 0 ≤ 𝑃(𝑥) ≤ 1.

2. The values of x are exhaustive: The probability of all distributions
includes all possible values.
3. The values are mutually exclusive: Only one value can occur for a
given experiment.
4. The sum of their probabilities is one.
 Discrete Probability Distribution
Example 2 A financial counselor conducts investment seminars with each seminar limite
d to 6 attendees. Because of the small size of the seminar group and the per
sonal attention each person receives, some of the attendees become clients f
ollowing the seminar. For the past 20 seminars she has conducted, x (for x =
the number of attendees who become clients) has had the relative frequency
distribution shown in Figure below.
Twenty investment seminars: Discrete
probability distribution for the random
variable x = number of attendees who
become clients

x P(x)
0 0.05
1 0.10
2 0.20
3 0.25
4 0.15
5 0.15
6 0.10
 General formulas for the mean and variance of a
discrete probability distribution

Mean
𝜇 = 𝐸 𝑥 𝑜𝑟 𝜇 = ෍ 𝑥𝑖 𝑃 𝑥𝑖 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑝𝑜𝑠𝑠𝑖𝑏𝑙𝑒 𝑣𝑎𝑙𝑢𝑒𝑠 𝑜𝑓 𝑥

Variance

𝜎 2 = 𝐸[ 𝑥 − 𝜇)2 𝑜𝑟 𝜎 2 = ෍(𝑥𝑖 − 𝜇)2 𝑃 𝑥𝑖 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑝𝑜𝑠𝑠𝑖𝑏𝑙𝑒 𝑣𝑎𝑙𝑢𝑒𝑠 𝑜𝑓 𝑥

 The Binomial Distribution
The binomial distribution deals with consecutive trials, each of which
has two possible outcomes.

Characteristics of a Bernoulli Process:

1. There are two or more consecutive trials.
2. In each trial, there are just two possible outcomes – usually denoted
as success or failure.
3. The trials are statistically independent; that is, the outcome in any
trial is not affected by the outcomes of the later trials.
4. The probability of a success remains the same from one trial to the
next.
 The Binomial Probability Distribution
The probability of exactly x successes in n trials is:
𝑃 𝑥 = 𝑛𝐶𝑟 × 𝜋 𝑥 × (1 − 𝜋)𝑛−𝑥

where:
𝑛 = 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑡𝑟𝑖𝑎𝑙𝑠
𝑥 = 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑠𝑢𝑐𝑐𝑒𝑠𝑠𝑒𝑠
𝜋 = 𝑡ℎ𝑒 𝑝𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦 𝑜𝑓 𝑠𝑢𝑐𝑐𝑒𝑠𝑠 𝑖𝑛 𝑎 𝑔𝑖𝑣𝑒𝑛 𝑡𝑟𝑖𝑎𝑙
1 − 𝜋 = 𝑡ℎ𝑒 𝑝𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦 𝑜𝑓 𝑓𝑎𝑖𝑙𝑢𝑟𝑒 𝑖𝑛 𝑎 𝑔𝑖𝑣𝑒𝑛 𝑡𝑟𝑖𝑎𝑙

Mean
𝜇 = 𝐸 𝑥 = 𝑛𝜋

Variance
𝜎 2 = 𝐸[ 𝑥 − 𝜇)2 = 𝑛𝜋(1 − 𝜋)
 The Binomial Probability Distribution
The binomial distribution is really a family of distributions, and the exact member of the family is
determined by the values of n and π. The following observations may be made regarding the Bernoulli
process and the requirement that the probability of success (π) remain unchanged:

1. If sampling is done with replacement (the person or other item selected from the population is
observed, then put back into the population), π will be constant from one trial to the next.

2. If, when sampling without replacement, the number of trials (n) is very small compared to the
population (N) of such trials from which the sample is taken, as a practical matter π can be
considered to be constant from one trial to the next. This would occur, for example, if n = 5
interview participants were randomly selected from a population of N = 1000 persons. As a rule of
thumb, if the population is at least 20 times as large as the number of trials, we will assume the
“constant π” assumption has been satisfactorily met.
 Binomial Probability Distribution
Example 4 Of the 18,000,000 part-time workers in the United States, 20% participate in retirement
benefits. A group of 5 people is to be randomly selected from this group, and the discre
te random variable is x = the number of persons in the group who participate in retirem
ent benefits.

a) What Is the Expected Value of x?

𝐸 𝑥 = 5 0.2 = 1.0

b) What Is the Probability That the Group Will Include Exactly Two Participants?

𝑃 𝑥 = 5𝐶2 × 0.22 × (1 − 0.2)5−2 = 0.2048

c) What Is the Probability That the Group Will Include at Least Three Persons Who Are P
articipants?
𝑃 𝑥 ≥3 =𝑃 𝑥 =3 +𝑃 𝑥 =4 +𝑃 𝑥 =5
𝑃 𝑥 ≥ 3 = 0.051 + 0.006 + 0.000 = 0.057
 Using the Binomial Tables
Example 4 a)What Is the Probability That the Group Will Include Exactly Two Participants?

b) What Is the Probability That the Group Will Include at Least Three Persons Who Are P
articipants?
 The Hypergeometric Distribution
The hypergeometric probability distribution is similar to the binomial in focusing on the number of
successes in a given number of consecutive trials, but there are two major differences:

First, the consecutive trials are not independent; that is, the outcome in a trial can be affected by
the outcomes in earlier trials, and can in turn affect the outcomes in later trials

Second, the probability of success does not remain constant from one trial to the next.

The distinction between the binomial and hypergeometric distributions can also be viewed in terms of
sampling with replacement versus sampling without replacement. In sampling without
replacement, the object selected from the population is not returned to the population. When sampling
is done without replacement and the population is not very large, the probability of a success can
change quite drastically from one trial to the next.
 The Hypergeometric Distribution
The probability of exactly x successes in n trials that are not independent is
(𝑆𝑪𝑥)(𝑁 − 𝑠)𝑪(𝑛 − 𝑥)
𝑃 𝑥 =
𝑁𝑪𝑛
where:
𝑁 = 𝑆𝑖𝑧𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛
𝑛 = 𝑠𝑖𝑧𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑠𝑎𝑚𝑝𝑙𝑒
𝑠 = 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑠𝑢𝑐𝑐𝑒𝑠𝑠𝑒𝑠 𝑖𝑛 𝑡ℎ𝑒 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛
𝑥 = 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑠𝑢𝑐𝑐𝑒𝑠𝑠𝑒𝑠 𝑖𝑛 𝑡ℎ𝑒 𝑠𝑎𝑚𝑝𝑙𝑒

Mean
𝑛𝑠
𝜇=𝐸 𝑥 =
𝑁

Variance
𝑛𝑠(𝑁 − 𝑠) 𝑁 − 𝑛
𝜎 2 = 𝐸[ 𝑥 − 𝜇)2 = ∙
𝑁2 𝑁−1
 Using the Binomial Tables
Example 5 Twenty businesses located in a small community have filed tax returns for the preceding
year. Six of the returns were filled out incorrectly. An Internal Revenue Service (IRS) audit
or randomly selects four returns for further examination, and the random variable is x =
the number of examined returns that are incorrectly filled out.

a) What Is the Expected Value of x?

𝑛𝑠 4(6)
𝐸 𝑥 = = = 1.20 𝑖𝑛𝑐𝑜𝑟𝑟𝑒𝑐𝑡 𝑟𝑒𝑡𝑢𝑟𝑛𝑠
𝑁 20
b) What Is the Probability That There Will Be Exactly Two Incorrect Returns A
mong the Four That Are Chosen for Further Examination?
(𝑆𝑪𝑥)(𝑁 − 𝑠)𝑪(𝑛 − 𝑥)
𝑃 𝑥 =
𝑁𝑪𝑛
(6𝑪2)(20 − 6)𝑪(4 − 2)
𝑃 𝑥 =
20𝑪4
𝑃 𝑥 = 0.2817
 The Poisson Distribution
The Poisson distribution is a discrete probability distribution that is applied to events for which the
probability of occurrence over a given span of time, space, or distance is extremely small. The discrete
random variable, x, is the number of times the event occurs over the given span, and x can be 0, 1, 2, 3,
and so on, with (theoretically) no upper limit. Besides its ability to approximate the binomial
distribution when n is large and 𝜋 is small, the Poisson distribution tends to describe phenomena like
these:
• Customer arrivals at a service point during a given period of time, such as the number of motorists
approaching a tollbooth, the number of hungry persons entering a McDonald’s restaurant, or the
number of calls received by a company switchboard. In this context it is also useful in a
management science technique called queuing (waiting-line) theory.
• Defects in manufactured materials, such as the number of flaws in wire or pipe products over a
given number of feet, or the number of knots in wooden panels for a given area
• The number of work-related deaths, accidents, or injuries over a given number of production hours
• The number of births, deaths, marriages, divorces, suicides, and homicides over a given period of
time
 The Hypergeometric Distribution
The probability that an event will occur exactly x times over a given span of time, space, or distance is
𝜆𝑥 𝑒 −𝜆
𝑃 𝑥 =
𝑥!
where:
𝜆 = 𝑡ℎ𝑒 𝑚𝑒𝑎𝑛, 𝑜𝑟 𝐸 𝑥 ; 𝑡ℎ𝑒 𝑒𝑥𝑝𝑒𝑐𝑡𝑒𝑑 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑜𝑐𝑐𝑢𝑟𝑒𝑛𝑐𝑒𝑠 𝑜𝑣𝑒𝑟 𝑡ℎ𝑒 𝑔𝑖𝑣𝑒𝑛 𝑠𝑝𝑎𝑛
𝑒 = 𝑡ℎ𝑒 𝑚𝑎𝑡ℎ𝑒𝑚𝑎𝑡𝑖𝑐𝑎𝑙 𝑐𝑜𝑛𝑠𝑡𝑎𝑛𝑡, 2.71828…
 The Poisson Distribution
Example 6 In an urban county, health care officials anticipate that the number of births this year wil
l be the same as last year, when 438 children were born—an average of 438/365, or 1.2
births per day. Daily births have been distributed according to the Poisson distribution

a) What Is the Mean of the Distribution?

b) Calculate Each of the Following Probabilities: P(x = 1), P(x = 2), P(x = 3), P(x = 4), an
d P(x = 5)
1.21 𝑒 −1.2
𝑃 𝑥=1 = = 0.3614
1!
1.22 𝑒 −1.2
𝑃 𝑥=2 = = 0.2169
2!
1.23 𝑒 −1.2
𝑃 𝑥=3 = = 0.0867
3!
1.24 𝑒 −1.2
𝑃 𝑥=4 = = 0.0260
4!
1.25 𝑒 −1.2
𝑃 𝑥=5 = = 0.0062
5!
 Using the Binomial Tables
Example 6 In an urban county, health care officials anticipate that the number of births this year wil
l be the same as last year, when 438 children were born—an average of 438/365, or 1.2
births per day. Daily births have been distributed according to the Poisson distribution

a) What Is the Mean of the Distribution?

b) Calculate Each of the Following Probabilities: P(x = 1), P(x = 2), P(x = 3), P(x = 4), an
d P(x = 5)