CHAPTER 4: A Survey of Probability Concept

1. Introduction

- Descriptive Statistic is concerned with summarizing data collected from past event

- Second facet of statistics – computing the chance that something will occur in the
future  Statistical Inference or Inferential Statistics.

- Statistical inference – deal with conclusion about a population based on a sample

taken from that population

- Because they are uncertainty in decision making  its important that all the known
risks involved be evaluated.

- This evaluation is probability theory  referred to as the science of uncertainty 

allow decision maker to analyze risks and benefits

- Introducing the field of statistical inference  Experiment, Event, Subject, and

addition and multiple rules.

2. What is Probability

- Probability, chance and likelihood- often used interchangeably

- What is Probability?

 A value between 0 and 1 – inclusive – describing the relative possibility (chance of

likelihood and event will occur)

 The probability of 1 means something that is certain to happen and probability of

0 means something cannot happen.

 The closer a probability is to 0  the more impossible/improbable is the event will

happen

 The closer the probability is to 1  the more likely it will happen

- Likelihood of an event is represented by using the term odd.

- 3 key words are used in study of probability: Experiment, Outcome and Event
- Experiment: has 2 or more possible results and it’s uncertain which will occur.
EX: Tossing a coin is an experiment – ensure the outcome either will come up
“heads” or “tails” – If the coin is tossed – 1 particular outcome is “head” – alternative
outcome is “tail”.
Event: One or more of experiment’s outcomes are observed  they call an event
Ex: ask 500 students if they willing to travel more than 200km to attend JB concert
 1 possible outcome is that 273 students will go
another outcome – 317 students will go
 another outcome – 423 student will go
 Those outcomes are called Event

3. Approaches To Assigning Probability

3 ways to assign the probability to an event: Classical, Empirical, and Subjective

Classical and Empirical methods are objectives and based on information and databe

The Subjective methods is based on person’s belief of an event’s likelihood.

a. Classical Probability

Classical probability is based on assumption that the outcomes of an experiment are

equal likely – Using classical viewpoint – the probability of an event happening is
computed by dividing the number of favourable outcomes by the number of possible
outcomes.
Mutually Exclusive: the occurrence of 1 event means that one of other
events can occur at the same time.

We can create classes so that particular event is included in only one of the
classesand there is no overlap between classes  Oly one of several events can
occur at a particular time

Decision to obtain a 4 years program represents mutually inclusive outcomes  A

high school student decides whether to attend a class or not – but can’t do both at
the same time

Manufactured part is defective or non-defective – can be both at the same time.

Collectively Exhaustive: if an experiment has a set of events that include every

possible outcome such as events ” an even number” and “odd number” in the die-
tossing experiment then set of the event is collectively exhaustive.

Collectively Exhaustive means at least 1 of the events must occur when an

experiment is conducted.

If the set of the events is collectively exhaustive and the events are mutually
exclusive – Sum of probabilities = 1.

Classical approach can be applied to lotteries:

 Example: a game of “pick 3” – a person buys a lottery ticket and selects 3 number
between 0-9 – once per week, 3 numbers are randomly selected from the machine
that tumbles 3 containers, each with balls 09  1 way to win is to match the
numbers and order of numbers.

b. Empirical Probability

- Empirical probability: The probability of an event happening is the fraction of the

time similar events happened in the past.
- Empirical probability or relative frequency is the second type of objective
probability. It’s based on the number of the time an event occurs as a proportion of a
known number of trials.

The Empirical approach to probability is based on law of large numbers.

Law of large numbers: over a large number of trials, the empirical probability of an
event will approach its true probability.
The key to establishing probabilities empirically is that more observations will provide
a more accurate estimate of probability.
Tossing the coin a great number of times  probability of the outcome of heads will
approach 0.5 times and then compute the relative frequency of heads.
Note: we increase number of trials – the empirical probability of head appearing
approaches 0.5 which is its value based on the classical approach.
c. Subjective Probability

If there is little or no experience of info on which to base a probability  its estimated

subjectively  means individual evaluates the available opinions and other info and
then estimate or assigns the probability  this is call subjective probability

Subjective probability – the likelihood (probability) of a particular event happening

that is assigned by an individual on the basis of whatever info is available.

Ex: Estimating the likelihood of the next Federal election happening within the next
year.

Estimating the likely hood you will be married before the age of 30

Estimating the chance of the Toronto Maple Leafs winning the Stanley Cup
 A probability statement always assigns a likelihood to an event that has not yet
occurred.

4. Principles of Counting

There are 3 fomulas will be examinated: Multiplication formula, permutation fomular

and combination formula.

a) Multiplication Fomula

- Multiplication formula: if there are m ways of doing one thing and n ways of
doing another thing, there are m*n ways of doing both.

- In previous applications, There were 2 or more grouping from which you made
selection
- Multiplication formula applied to find the number of possible outcomes for 2 or more
groups.

b) The Permutation Formula

Permutation formula is applied to find the possible number of arrangements

when there is only one group of objects.

Permutation is any arrangement of r objects selected from a single group of n

possible objects when order is considered.

Not arrangement of b a c and b a c are different permutations. Formula is:

Permutation is the order is matter

c) The Combination Formula

If the order of selected objects is not important – any selection is called a

combination.

Formula to count the number of r object combinations from a set of n is:

NOTE: Number of Combination is always less than the number of permutations

5. Some Rules For Computing Probabilities

2 Rules of addition: the special rule of addition and the general rule of addition

A. Special Rule of Addition – Mutually Exclusive

Recall: Mutually exclusive – when 1 event occur – other event cannot be occured
at the same time – die tossing experiment. It cannot be both defective and non-
defective at the same time.

If 2 events A and B are exclusive – the special rule of addition states that the
probability of occurrence of 1 event or the other equals the sum of their probabilities
 Venn diagram – portrait graphically the outcome of an experiment

The mutually exclusive concept and various other rules for combining probabilities
can be illustrated using this device.

To construct the Venn diagram – a space is first enclosed – representing the totalof
possible outcomes. This space is usually in form of a rectangle

An event is then represent by a circular area, which is drawn inside the rectangle
proportional to the probability of the event.

The following Venn diagram represents the mutually exclusive concept – there is
no overlapping of the events, meaning that the events are mutually exclusive.

 Compliment Rule

The probability that a bag of mixed vegetables selected is underweight P(A) + the
probability that the bag is not an underweight bag P(~A) (not A) must be equal 1

P(A) + P(~A)=1

 The complimentary rule: is used to determine the probability of an event

occurring by subtracting the probability of the event not occurring form 1.
This rule is useful b/c its easier to calculate the probability of an event happening by
determining probability of it not happening and subtracting the result from 1.

Note: events A and (~A) are mutually exclusive and collectively exhaustive  The
probabilities of A and ~A sum to 1.

Venn Diagram illustrating compliment rule is:

B. The General Rule of Addition

The outcomes of an experiment may not be mutually exclusive

  ex: 200 tourist visited Toronto during festival time. The survey showed that 120
tourists visited CN towel and 100 went to Toronto Island for festival. What’s the
probability that the tourist selected visited either CN tower or Toronto Island.

If its special rule of addition is used:

 visit CN tower = 120/200=0.6

 Visit Toronto Island = 100/200=0.5

Sum of these 2 probabilities = 1.1 but probability can’t be greater than 1 so some
visitors visit both places  its being count twice. A check of survey said 60 out of 200
visited both.

So, What the probability a selected tourist visited either CN tower or Toronto island?

We need to add the probability that tourist visit CN Tower and Toronto island and then
subtract the probability of visiting both (60/200=0.3)

 Joint probability – a probability that measure the likelihood of 2 or more events will
happen concurrently – 2 events both occur at the same time.

For P(A and B) -> the word or suggest that A may occur or B may occur  this
includes probability that A and B may occur – this use of or is called an inclusive
If we compare the general and special rules of addition  the most important
difference is determining if the events are mutually exlusive.
 If the event are mutually exclusive  then joint probability P(A or B) is 0 and we
could use special rule of addition.
If the event are not mutually exclusive  we must count for the joint probability P
(A and B) and we use the general rule of addition.
5. Rules of Multiplication
- Rules of computing the likelihood that 2 events both happen, or joint probability
 Venn Diagrams illustrate the intersection of 2 events  to find the likelihood of 2
event happening we use rules of multiplication  2 rules of multiplication – special
rule and general rule
 Special Rule of Multiplication
Requiring 2 events A and B – both are independent
Independent event mean the occurrence of the event has no effect on the probability
of the occurrence of another event.
Another saying – event A and B occur at different time.
Ex: Event B occurs – does A has any effect on the occur of B? If answer is no -> A and
B are independent events.
For 2 independent events A and B the probability that A and B both will occur s found
by multiplying 2 probabilities  Special rule of multiplication:

For the experiment of tossing 2 coins – the probability of 2 head P (H and H) = (1/2)
(1/2)= ¼
For 3 independent events A, B and C the special rule of multiplication used to
determine the probability that all 3 events will occur:
P (A and B and C) = P(A) *P(B)*P(C)
Experiment of tossing 3 coins  P (H and H and H)= ½*1/2*1/2= 1/8
 With the probabilities and the compliment rule, we can compute the joint
probability of each outcome
Ex: the probability neither student receives a grade of B or better is 0.16
The probability of the first or the second student (special addition) receive the grade
of B or better is 0.48*(0.24+0.24)
You can observe the outcomes are mutually exclusive and collectively exclusive 
the probability sum = 1

 General Rule of Multiplication

 If 2 events are not independent  they are dependent
 Conditional probability means the probability of a particular event occurring, given
that another events has occurred.
In general rule of multiplication – the conditional probability is required to compute
the joint probability of 2 events that are not independent (dependent).
For 2 event A and B, that are dependent, the conditional probability is represent as P
(B
|A) the “|” is a mathematical symbol for expression “given that”  P (B|A) is the
probability of event B happening given that A has already happened. Or, the
probability of B is conditional on the outcome of A
Note: All possible outcomes of selecting 2 cans of soda without replacement (k bỏ
vào lại) are considered. Therefore, probabilities = 0.0667 + 0.2333+0.2333+0.4667
=1
Chú í replacement quan trọng trong test.
It is assumed this experiment was conducted without REPLACEMENT  means take
the shirt and did not put back in closet before the second one selected.
 outcome of the second one is conditional or dependent on outcome of the first
event.
 we can general rule of multiplication to more than 2 events  for 3 events: A, B
and C formula will be:

So the likelihood of selecting these 3 shirt without replacement and all being white is
0.38
6. Contingency Tables
We tally the results of the sample n 2-way table and use the results of this tally to
determine various probabilities
Contingency table used to classify sample observations according to 2 or more
identifiable categories or classes.
A contingency table is a cross-tabulation that summarize 2 variables of interest and
their relationship.
7. Tree Diagrams
The tree diagram is the graph help organize and calculate the probabilities for the
problems.
This type solve several stages – each stage is illustrated with a branch of the tree
The branches of a tree diagram are labelled with probabilities
To construct the tree diagram:
1. Drawing a heavy dot on the left to represent the root of the tree
2. For this problem, there are 2 main branches going out from the root. Upper branch
represents the outcome “would remain”
Lower branch represents the outcome “would not remain”  their probabilities are
written on the branches, namely, 120/200 and 80/200  these could also be denoted
P(A1) P(~A1)
3. Four branches “grow” out of each 2 main branches  these branches represent
the length of service. The conditional probabilities for upper branch are written on
appropriate branches
Next write conditional probabilities for the lower branch.
4. Finally, we determine the various joint probabilities. That event A1 and B1 or the
event A2 and B1 will occur together, are shown on the right side.

A1 and B2
are mutually
A1 and B1
are not Collectively
mutually exhausted
Unconditional
And mutually
exclusive

In the chart, joint probabilities for all possible combination of loyalty (“wound
remain” and “would not remain” and service (<1 year, 1-5 year, 6-10 years and
over 10 years are computed.

Because all possible outcomes are listed- the sum of the joint
probabilities must equal 1.00