Business Statistics

Black, Bayley, Castillo

Third Canadian Edition

Chapter 4

Probability

Copyright ©2020 John Wiley & Sons, Canada Ltd.

Introduction to Probability
• (Random) Experiment: a process that produces well-defined outcome(s)
o Sampling every 200th bottle of cola and weighing it
o Auditing every 10th account
o Testing drugs on patients and recording outcomes
• Event: an outcome of an experiment
o There are 10 bottles that are too full
o There are 3 accounts with problems
o Half of the patients improve
• Elementary event: event that cannot be decomposed or broken down into other events
o Elementary events are denoted by lowercase letters
o Suppose that the experiment is to roll a die
o Elementary events are to roll a 1, a 2, a 3, etc.
o In this case, there are six elementary events, e1, e2, etc.

Copyright ©2020 John Wiley & Sons, Inc. 2

1
Introduction to Probability

• Sample Space: a complete listing of all elementary events

(all possible outcomes ) for a random experiment
o Rolling a single die: sample space is {1,2,3,4,5,6}
o Rolling 2 dice: the sample space has 36 elementary events
Possible Outcomes for the Roll of a Pair of Dice Possible Outcomes for the Rolling of a Die and Flipping a coin

Copyright ©2020 John Wiley & Sons, Inc. 3

Introduction to Probability
Sample Space Example: Construct a sample space that
describes all three-child families according to the genders of the
children with respect to birth order.

S={bbb,bbg,bgb,bgg,gbb,gbg,ggb,ggg}

Copyright ©2020 John Wiley & Sons, Inc. 4

2
Introduction to Probability
Classical Method of Assigning Probabilities
• The probability of an individual event occurring is determined by the
ratio of the number of items in a population that contain the event (ne)
to the total number of items in the population (N)
o Each outcome is equally likely n
P(E) = e
N
where
N = total number of possible outcomes of an experiment
ne = the number of outcomes in which the event occurs

Copyright ©2020 John Wiley & Sons, Inc. 5

Introduction to Probability
Classical Method of Assigning Probabilities
The following figure expresses the content of the definition of the probability of an
event:

Since the whole sample space S is an event that is certain to occur, the sum of
the probabilities of all the outcomes must be the number 1.

Copyright ©2020 John Wiley & Sons, Inc. 6

3
Introduction to Probability
Classical Method of Assigning Probabilities

A die is called “balanced” or “fair” if each side is equally likely to land on top.
Assign a probability to each outcome in the sample space for the experiment that
consists of tossing a single fair die. Find the probabilities of the events
E: “an even number is rolled” and
T: “a number greater than two is rolled.”

Solution:

With outcomes labeled according to the number of dots on the top face of the die,
the sample space is the set

S={1,2,3,4,5,6}
E={2,4,6},
T= ={3,4,5,6},

Copyright ©2020 John Wiley & Sons, Inc. 7

Introduction to Probability
Classical Method of Assigning Probabilities
• Because ne can never be greater than N, the highest value of a
probability is 1
• The lowest probability, if none of the N possibilities has the desired
characteristic, e, is 0
• Thus 0 ≤ P(E) ≤ 1
• A priori probability (classical probability)– the probability can be
determined before the experiment takes place
o Example: Machine A always produces 40% of products and always has a
10% defective rate
o Thus the probability of that a product is defective and came from Machine
A is 0.4 * 0.1 = 0.04

Copyright ©2020 John Wiley & Sons, Inc. 8

4
Introduction to Probability
Relative Frequency of Occurrence (Empirical probability)
• Probability of an event occurring is equal to the number of times the
event has occurred in the past divided by the total number of
opportunities for the event to have occurred
Number of Times an Event Occured
P(E) =
Total Number of Opportunities for the Event to Have Occured
• Based on historical data; the past may or may not be a good predictor
of the future
• Example: a company wants to know the probability that its inspectors
will reject a shipment from a particular supplier
o They have received 90 shipments in the past and rejected 10
10
o Thus the probability that they will reject is 90 = 0.11
Copyright ©2020 John Wiley & Sons, Inc. 9

Introduction to Probability
• CP&L is starting a project designed to increase the generating capacity of
one of its plants in southern California.
• Analysis of similar construction projects indicates that the possible
completion times for the project are 8, 9, 10, 11, and 12 months.

Copyright ©2020 John Wiley & Sons, Inc. 10

5
Introduction to Probability
Subjective Probability
• Based on the insights or feelings of the person determining the
probability
• Different individuals may (correctly or incorrectly) assign
different numeric probabilities to the same event
• subjective approach is usually limited to experiments that are
unrepeatable
• Examples:
o An experienced airline mechanic estimates the probability that a
particular plane will have a certain type of defect
o A doctor assigns a probability to the expected life span of a patient
with a specific type of cancer
Copyright ©2020 John Wiley & Sons, Inc. 11

Structure of Probability
Venn Diagram for Event A: To illustrate the logical relation
between sets
• Rectangular area represents the sample space for the random
experiment and contains all possible outcomes.
• Circle represents event A and contains only the outcomes that belong
to A.
• Shaded region of the rectangle contains all outcomes not in event A.

6
Structure of Probability
• Mutually Exclusive Events
o Events with no common outcomes
o Occurrence of one event precludes the occurrence of the other
event
o Example: if you toss a coin and get heads, you cannot get tails
FIGURE 4.5 Mutually Exclusive Events X and Y

Copyright ©2020 John Wiley & Sons, Inc. 13

Structure of Probability
Collectively Exhaustive Events
o Contains all possible elementary events for an experiment
• Rolling a die: {1,2,3,4,5,6}
• Generating a random integer number: { >5,= <5}
o The sample space for an experiment can be described as mutually
exclusive (events do not have any outcome in common) and
collectively exhaustive

Copyright ©2020 John Wiley & Sons, Inc. 14

7
Structure of Probability
Complementary Events
o Given an event X, the complement of X is defined to be the
event consisting of all outcomes that are not in X.
o Complementary events are denoted X′ (or 𝑋 ), which is
pronounced as “not X”
o In any probability application, either event X or its complement X′
must occur.
P(X′) = 1 − P(X)

Copyright ©2020 John Wiley & Sons, Inc. 15

Structure of Probability

Unions and Intersections FIGURE 4.3

• Set notation is the use of braces to group numbers A Union
o The union of sets X, Y is denoted X ∪ Y

• Given two events X and Y, the union of X and

Y is defined as the event containing all
outcomes belonging to X or Y or both
FIGURE 4.4 An
Intersection
o The intersection of sets X, Y is denoted X ∩ Y
• An element is part of the intersection if it is in
set X and set Y

Copyright ©2020 John Wiley & Sons, Inc. 16

8
Addition Laws
The General Law of Addition (addition law) is used to find
the probability of the union of two events
• The probability that event A or event B or both will
occur (at least one of two events will occur).
P ( X ∪ Y ) = P ( X ) + P (Y ) − P ( X ∩ Y )

A special case arises for mutually exclusive events.

Copyright ©2020 John Wiley & Sons, Inc. 17

Addition Laws

Copyright ©2020 John Wiley & Sons, Inc. 18

9
4.2 Structure of Probability
• Mutually Exclusive Events

Copyright ©2020 John Wiley & Sons, Inc. 19

Addition Laws
Addition Law Example:
• Workers were asked which changes in office design would increase
productivity
• 70% chose noise reduction (N), 67% chose more storage space (S)
• 56% chose both noise reduction and more space
• What is the probability that a person chooses either noise reduction
or more storage space?

Copyright ©2020 John Wiley & Sons, Inc. 20

10
 Addition Laws

Figure 4.8 Solving for the Union in the Office Productivity

Problem
P ( N ) = .70
P ( S ) = .67
P ( N ∩ S ) = .56
P ( N ∪ S ) = .70 + .67 − .56
= 0.81

Copyright ©2020 John Wiley & Sons, Inc. 21

Addition Laws
A probability matrix displays the intersection (joint) probabilities along
with the marginal probabilities of a given problem
• When values give the probability of the intersection of two
events, the probabilities are called joint probabilities.
o Inner cells show joint probabilities
• Marginal probabilities are found by summing the joint probabilities in the
corresponding row or column of the joint probability table.
o Outer cells show marginal probabilities

P( N ∪ S ) = P( N ) + P( S ) − P( N ∩ S )
= .70 + .67 − .56 = .81

Copyright ©2020 John Wiley & Sons, Inc. 22

11
Marginal, Union, Joint, and Conditional
Probabilities
FIGURE 4.7 Marginal, Union, Joint, and Conditional Probabilities

Copyright ©2020 John Wiley & Sons, Inc. 23

Structure of Probability
Counting the Possibilities
The mn Counting Rule:
• If an operation can be done m ways and a second operation can be done
n ways, then there are mn ways for the two operations to occur in order
o A cafeteria offers 5 salads, 4 meats, 8 vegetables, 3 breads, 4 desserts, and
3 drinks
• How many meals are available?
• 5 × 4 × 8 × 3 × 4 × 3 = 5760
Sampling from a Population with Replacement:
• Sampling n items from a population of size N with replacement would begin underline end underline

provide (N)n possibilities

o Six lottery numbers are drawn from the digits 0 to 9, with replacement
• There are (10)6 = 1,000,000 possible outcomes
Copyright ©2020 John Wiley & Sons, Inc. 24
Source: https://www.stat.purdue.edu/~huang251/slides4.pdf

12
Structure of Probability
Counting the Possibilities
Combinations: Sampling from a Population without Replacement
• Sampling n items from a population of size N without replacement
provides the following number of possibilities
o
N N!
Cn =   =
N
 
n n !( N − n )!

o A small law firm has 16 employees and 3 are to be selected randomly to

represent the company at the annual meeting of the American Bar
Association
• How many combinations of employees are possible?
16!
N Cn =16 C3 = = 560
3!13!
Copyright ©2020 John Wiley & Sons, Inc. 25

Independent Events
o The occurrence or nonoccurrence of one event does not affect the
occurrence or nonoccurrence of the other event(s)
o The probability of someone wearing glasses is unlikely to affect
the probability that the person likes milk
o Many events are not independent
•
The probability of carrying an umbrella changes when the weather
forecast predicts rain
If events are independent, then:

P ( X | Y ) = P ( X ) , and P (Y | X ) = P (Y )

P( X |Y ) is the probability that X occurs given that Y has occurred.

begin underline end underline

Copyright ©2020 John Wiley & Sons, Inc. 26

13
Conditional Probability
• Conditional probability: When the probability of
one event is dependent on whether some related
event has already occurred.
• Illustration: Lancaster Savings and Loan:
• Interested in mortgage default risk.
• Interested in whether the probability of a customer defaulting differs
by marital status.

Conditional Probability
Table: Subset of Data from 300 Home Mortgages of
Customers at Lancaster Savings and Loan

Total
Customer Marital Annual Mortgage Payments Amount Default on
No. Age Status Income Amount per Year Paid Mortgage?
1 37 Single $172,125.70 $473,402.96 24 $581,885.13 Yes
2 31 Single $108,571.04 $300,468.60 12 $489,320.38 No
3 37 Married $124,136.41 $330,664.24 24 $493,541.93 Yes
4 24 Married $79,614.04 $230,222.94 24 $449,682.09 Yes
5 27 Single $68,087.33 $282,203.53 12 $520,581.82 No
6 30 Married $59,959.80 $251,242.70 24 $356,711.58 Yes

14
Conditional Probability
Data from 300 Home Mortgages of Customers at
Lancaster Savings and Loan
Table: Crosstabulation of Marital Status and if Customer Defaults on
Mortgage
Marital Status No Default Default Total
Married 64 79 143
Single 116 41 157
Total 180 120 300

• From Table 5.4 or Figure 5.5, the probability that a customer defaults on his or
her mortgage is 120 300 = 0.4.
• The probability that a customer does not default on his or her mortgage is
1 − 0.4 = 0.6 or 180 300.

Conditional Probability
• Conditional probabilities can be computed as the ratio of joint probability to a
marginal probability.

15
 Conditional Probability

Joint Probability Table for Customer Mortgage

Prepayments

Probability of a customer defaulting Given they are married = 0.2633/0.4766

Probability of a customer defaulting Given they are not married = 0. 1367/0.5234

Conditional Probability

16
Multiplication Laws
General Law of Multiplication

P ( X ∩ Y ) = P ( X ) ⋅ P (Y | X ) = P (Y ) ⋅ P ( X | Y )

• Used to find the joint probability

Copyright ©2020 John Wiley & Sons, Inc. 33

Multiplication Laws
General Law of Multiplication
• Example: A company has 140 employees, of which 30 are
supervisors (S). Eighty of the employees are married (M), and
20% of the married employees are supervisors. If a company
employee is randomly selected, what is the probability that the
employee is married and is a supervisor?
𝑃(𝑆) = = 0.2142 𝑃 𝑀 𝑆 = ? Not given

80
P(M ) = = .5714 𝑃 𝑆 𝑀 = 0.2 given
140
P ( M ∩ S ) = P ( M ) ⋅ P ( S | M ) = (.5714 )(.20 ) = .1143

Copyright ©2020 John Wiley & Sons, Inc. 34

17
Multiplication Laws
Special Law of Multiplication
• If X and Y are independent,
P(X ∩ Y) = P(X) · P(Y)
• Example: A study found that 28% of Americans believe that the
ATM has had a most significant impact on everyday life (A). A
different study found that 71% of workers believe that working in
a team reduces stress (S). These studies are unrelated, so they can
be considered independent.
o What is the probability that a randomly selected person believes
that an ATM is significant AND is less stressed working in a team?
o P(A ∩ S) = P(A) . P(S) = (.28)(.71)= .1988

Copyright ©2020 John Wiley & Sons, Inc. 35

Conditional Probability
Independent Events
If events are independent, then

P ( X | Y ) = P ( X ) and P (Y | X ) = P (Y )

• Example: Recall that in the office productivity study, 70%

favored noise reduction, and 67% favored increases in storage
space. 56% believed that both would improve productivity.
o Are these events independent?
P ( S ∩ N ) .56
o P(S | N ) = = = .80 ≠ P ( S ) = .67
P(N ) .70
o Since these probabilities are not equal, these events are not
independent
o Could also check P ( N | S )
Copyright ©2020 John Wiley & Sons, Inc. 36

18
Conditional Probability
Law of Conditional Probability: the conditional probability of X
occurring, given that Y is known or has occurred is expressed

P ( X ∩ Y ) P ( X ) ⋅ P (Y | X )
P ( X |Y ) = =
P (Y ) P (Y )

• Example: Recall that in the office productivity study, 70%

favored noise reduction, and 67% favored increases in storage
space. 56% believed that both would improve productivity.
o What is the probability that a randomly selected person believes
storage space would increase productivity, given that he or she
believes that noise reduction improves productivity?
P ( S ∩ N ) .56
o
P(S | N ) = = = .80
P(N ) .70

Copyright ©2020 John Wiley & Sons, Inc. 37

Example:
Conditional Probability

• Example: A company has 140 employees, of which 30 are

supervisors (S). Eighty of the employees are married (M), and
20% of the married employees are supervisors. If a company
employee is randomly selected, what is the probability that the
employee is married if is a supervisor?
𝑃(𝑆) = = 0.2142 𝑃 𝑀 𝑆 = ? Not given

80
P(M ) = = .5714 𝑃 𝑆 𝑀 = 0.2 given
140

∗ ( | ) . ∗ .
𝑃 𝑀𝑆 = = = 0.54
( ) .

Copyright ©2020 John Wiley & Sons, Inc. 38

19
Conditional Probability

Copyright ©2020 John Wiley & Sons, Inc. 39

Revision of Probabilities: Bayes’ Rule

Bayes’ Rule extends the use of the law of conditional probabilities

to allow revision of original probabilities with new information
P ( X i ) P (Y | X i )
P ( Xi | Y ) =
P ( X 1 ) P (Y | X 1 ) + P ( X 2 ) P (Y | X 2 ) + …+ P ( X n ) P (Y | X n )

o The denominator is a weighted average of the conditional

probabilities, with the weights being the prior
probabilities
o The formula allows statisticians to incorporate new
information to revise probability estimates

Copyright ©2020 John Wiley & Sons, Inc. 40

20
Revision of Probabilities: Bayes’ Rule

Copyright ©2020 John Wiley & Sons, Inc. 41

Revision of Probabilities: Bayes’ Rule

Copyright ©2020 John Wiley & Sons, Inc. 42

21
Conditional Probability
• Example: A manufacturing firm receives shipments
of parts from two different suppliers:
• 65% of the parts purchased from supplier 1.
• 35% of the parts purchased from supplier 2.
• Quality of purchased parts varies according to their
source.

% Good Parts % Bad Parts

Supplier 1 98 2
Supplier 2 95 5

Conditional Probability

Figure 4.2: Diagram for Two-Supplier Example

Step 1 shows that
the part comes
from one of two
suppliers and Step
2 shows whether
the part is good or
bad.

22
 Conditional Probability

Figure 4.3: Probability Tree for Two-Supplier

Example

Revision of Probabilities: Bayes’ Rule

Figure 4.13 Tree Diagram for Over-the-Counter Drug Problem

Probabilities

Copyright ©2020 John Wiley & Sons, Inc. 46

23
Revision of Probabilities: Bayes’ Rule

Table 4.8 Bayesian Table for Revision of Over-the-Counter Drug

Problem Probabilities

Copyright ©2020 John Wiley & Sons, Inc. 47

24