Statistics 1

Chapter 5:
Probability

Statistics for Business and Economics

Sections 3.1 - 3.3 and 3.5

Dr Joan Gan
Dr Raymond Teo

Set Theory

Random Experiments,
Sample Spaces,
Events

Probability
2

1
Statistics 1

Random Experiment

A random experiment is a process leading to at least

two possible outcomes with uncertainty as to which will
occur.

E.g. when a coin is thrown

E.g. when a dice is rolled

Probability 3

Basic (or Elementary) Outcome

The Basic (or Elementary) Outcome represents the

different possible outcomes arising from a random
experiment.

e.g. when a dice is thrown, the basic outcomes are

1, 2, 3, 4, 5, 6

Probability 4

2
Statistics 1

Sample Space

The Sample Space is the set of all basic outcomes.

When a dice is rolled, the basic outcomes are 1, 2, 3, 4, 5, and 6.

The sample space S = [1, 2, 3, 4, 5, 6]

If the experiment is tossing a coin, the sample space is the set

S = [head, tail]

Probability 5

Event

An event is a subset of a sample space.

e.g. when a dice is thrown, an event that

might be of interest would be when the
resulting number is even, i.e. when the
basic outcome is 2, 4, or 6

Probability 6

3
Statistics 1

Illustrations

When tossing a coin, we could have the following:

S = {H, T} E = {H} or E = {T}

When throwing a dice:

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

Probability 7

Rules and Symbols:

UNIONS

Probability 8

4
Statistics 1

Rules and Symbols:

INTERSECTION

Probability 9

Rules and Symbols:

COMPLEMENT

Probability 10

5
Statistics 1

Illustration:

Probability 11

Mutually Exclusive Events

Events E1, E2, ..., En are said to be mutually exclusive if the

occurrence of any one of them automatically implies the non-
occurrence of the remaining n − 1 events. In other words, two
mutually exclusive events cannot both occur.

Examples
• A flipped coin coming up heads and the same coin
coming up tails at the same time are mutually exclusive
events.
• A student passing a test and failing it are mutually
exclusive

Probability 12

6
Statistics 1

A related concept: collectively

exhaustive

When events are collectively exhaustive, at least one

of the events must happen

e.g. in a toss of a dice, A = {1,2,3} B = {3,4,5,6}

Probability 13

Using a Venn diagram for

representation
In a throw of a dice, If E= {3,4} and F={4,5,6},
what is

S
E
F
3 4 6
5

1 2

Probability 14

7
Statistics 1

Definitions of Probability

Probability
15

Probability – A priori

Probability 16

8
Statistics 1

Illustration

In a throw of two dices, what is the probability that both

are sixes.

Total number of possible outcomes, N = 36

Event A = {(6,6)}

Number of outcomes in the event NA =1

Probability of outcome A occurring = 1/36

Probability 17

If you are told that at least one of the outcomes is a six,

what is the probability that both are sixes?

Possible outcomes where at least one is a six:

{(1,6), (2,6), (3,6), (4,6), (5,6), (6,6), (6,1), (6,2)
(6,3), (6,4), (6,5)}
Total number of outcomes with at least one six
appearing, N = 11

Outcomes with two sixes : {(6,6)}

Number of outcomes with two sixes = 1

P(both are sixes / at least one is a six) = 1/11

Probability 18

9
Statistics 1

What is the probability that both outcomes are odd?

Total number of outcomes, N = 36

Event A where both are odd {( ), ( ) ………)}

Total number of possible outcomes NA = 9

P(both odd) = 9/36 = ¼

Fill this in yourself

Probability 19

Probability – Frequency

An experiment is repeated many times. The

probability of an event is the limiting value of the
proportion of experiments in which the event occurs,
as the number of experiments tends to infinity.

Probability 20

10
Statistics 1

Think of throwing dices. If you continue throwing

dices for a very large number of times, say 500,
the probability of 1 occurring would be about 1/6.

Probability 21

Some axioms of probabilities

Given that E and F are events in a sample space S,
and that Φ is an empty set, the axioms are:

Probability 22

11
Statistics 1

Conditional probability

The conditional probability P(A|B) is the probability

that A happens given that B has already happened.

We call this Bayes’ formula. But it has other forms.

Probability 23

Probability 24

12
Statistics 1

Illustration

In a restaurant, if 75% of the customers use

mustard, 80% use ketchup, and 65% use both.
What are the probability that a ketchup user
uses mustard?

Probability 25

Independent Events

Two events are independent means that knowing

whether one of them occurs makes it neither more
probable nor less probable that the other occurs.

For example, the event of getting a "1" when a dice is thrown

and the event of getting a "1" the second time it is thrown are
independent.

Probability 26

13
Statistics 1

Independent Events

 Do you think how good a dancer you are is related to the

grades of your LSE examination?
 Do you think whether you are a part time or full time
student is related to the grades of your LSE
examination?

Now,

 Do you think the performance of your second test is

related to the performance of the first test?

Probability 27

Two more activities

There are three sites a company may move to: A, B, or C.

We are told that P(A) {the probability of a move to A) is ½,
and P(B) is 1/3. What is P(C)?

Obviously, the company cannot move to two sites at the same time.
Therefore the events are mutually exclusive.

For mutually exclusive events P(A U B) = P(A) + P(B) =1/2 + 1/3 = 5/6.
P(C) = 1 – P(A U B) = 1/6.

Probability 28

14
Statistics 1

A test of independence

If the probabilities of two events occurring are such that

Probability 29

Two events A and B are independent with probability (1/3) and

(1/4) respectively. What is P(A ∩ B)?

Since the two events are independent,

P(A ∩ B) = P(A) P(B)

= (1/3) (1/4)
= 1/12

Probability 30

15
Statistics 1

Probability Trees

Probability
31

The probability of emerging at the end of any path

through the diagram is found by multiplying the
probabilities on the branches on the path.

Probability 32

16
Statistics 1

There are 3 balls in a bag: black, white, and green. One ball
is picked out, and not replaced, and then another ball is picked
out.
1/6
P(white) = 1/2

P(green) = 1/2
P(black) = 1/3 1/6
P(black) = 1/2
P(white) = 1/3 1/6

P(green) = 1/2 1/6

P(green) = 1/3
P(black) = 1/2 1/6

P(white) = 1/2 1/6

Probability 33

Yellow Guide Activity:

A company gets 60% of its supply from manufacturer A, the

remainder from manufacturer Z. The quality of the parts delivered
is given below:

Manufacturer % of good parts % of bad parts

A 97 3
Z 93 7

Probability 34

17
Statistics 1

a) What is the probability that a randomly chosen part comes

from A and is bad?
b) What is the probability of receiving a bad part?

Tree Diagram For Part Defects

P(Part is good) = 0.97

P(Parts from A) = 0.6

a) Prob that randomly chosen part comes
from A and is bad = (0.6)(0.03) = 0.018
P(Part is bad) = 0.03

P(Part is good) = 0.93

P(Parts from B) = 0.4 b) Prob that randomly chosen part comes from
P(Part is bad) = 0.07 B and is bad = (0.4)(0.07) = 0.028.
Prob (part is bad) = 0.018 + 0.028 = 0.046

Probability 35

TOTAL PROBABAILITY FORMULA

(easily understood from the probability tree)

See what we did earlier

The total probability formula:

Probability 36

18
Statistics 1

Study guide eg: (WILL NOT BE DISCUSSED BUT I WOULD LIKE

YOU TO USE PROB TREES TO DO THIS)

In an audit Bill analyses 60% of the audit items and George analyses
40%. Bill’s error rate is 5% and George’s is 3%. Suppose an item is
sampled at random.
a. What is the probability that it is in error (audited incorrectly)?
b. If the chosen item is incorrect what is the probability that Bill is
to blame?

Let B = item audited by Bill, G = items audited by George, and

E = error audit.
Hence P(B) = 0.6, P(G) = 0.4, P(E|B) = 0.05 and P(E|G) = 0.03.

a. Using the total probability formula:

P(E) = P(E|B)P(B)+P(E|G)P(G) = (0.05×0.6)+(0.03×0.4) = 0.042

Probability 37

= 0.71

Probability 38

19