LECTURE 4

Probability
(Chapter 6)
 What is Probability?

 Probability is an essential component of inferential

statistics.

 It quantifies the degree of uncertainty or the

relative likelihood an event will occur.

 Probability theory also plays a critical role in

decision making.
 Basic Terms in Probability
 Experiment : An action or process that leads to one of several
possible outcomes.
 Flip a coin outcome?
 Flip a dice

 Sample space: A list of all possible outcomes of the experiment.

The outcomes must be:

exhaustive – all possible outcome must be included mutually
exclusive - two outcome cannot occur at the same time

 Event : collection of one or more of the possible outcomes of an

experiment. It is a subset of the sample space.

 The probability of any outcome or event expresses the chance that

the outcome or event will occur. It must lie between 0 and 1.
 Approaches to Assigning Probability

 Classical approach : describes probability in terms of

the proportion of times that an event can be
expected to occur – used by mathematician to
determine probability with game of chance

 Relative frequency approach : define probability as

the proportion of times that an event is observed
to occur in a very large number of trials.

 Subjective approach: define probability as the

degree of belief that we hold in the occurrence of an
event – based on experience
Example 1:
 Experiment: A fair coin is flipped for 3 times

 Sample Space:

S={HHH, HHT, HTH, HTT, THH, THT, TTH, TTT}

* The sum of the probabilities of all the outcomes

in a sample space must be 1

 Event:

A – obtain one head, A = {HTT, THT, TTH}

B – obtain three tails, B = {TTT}

 Simple and Complementary Events

 Simple event: An event that can be described by

a single characteristic.

The probability of an simple event will occur is known

as marginal probability.

 Complement event : The complement of event A

is the event that occurs when event A does not
occur.

The complement of event A is denoted by A’

Complement Rule : P(A) = 1 – P(A)

 Unions and Intersections of Events
 Intersections of events

The intersection of events A and B is the event

that occurs when both A and B occur.

It is denoted as A and B. The probability of the

intersection is called the joint probability.

 Unions of events

The union of events A and B is the event that occurs

when either A or B or both occur.

It is denoted as A or B.
 Addition Rule
 The addition rule enables us to calculate the probability
of the union of two events.

 Addition Rule :

P(A or B) = P(A) + P(B) – P(A and B)

 Mutually exclusive events

The occurrence of one event means that none of the

others can occur at the same time, i.e. P(A and B) =
0

P(A or B) = P(A) + P(B)

if A & B are mutually exclusive events
Example 2:
An accounting firm has advertised the availability of its
report describing recent changes to the federal income tax
act. The first 200 callers requesting a copy of the report
are classified in the following contingency table according
to the medium by which the caller became aware of the
report and the caller’s primary interest.

Primary Medium
interest Radio Newspaper Word of
(R) (N) mouth
(W)
Personal tax (C’) 34 20 26
Corporate tax (C) 36 70 14
One caller is selected at random, and four events are
defined as follows:

C: The caller is primarily interested in corporate tax.

R: The caller became aware of the report through

radio.

N: The caller became aware of the report through

newspaper.

W : The caller became aware of the report through

word of mouth.
It is easier for you if convert the
contingency table to relative frequency
table (in terms of fraction)
Example 2:
Medium Total
Primary Interest Radio (R) Newspaper (N) Word of
mouth (W)
Corporate tax (C) 36 70 14 120
Personal Tax (C’) 34 20 26 80
Total 70 90 40 200

Relative Frequency Table

Medium Total
Primary Interest Radio (R) Newspaper (N) Word of
mouth (W)
Personal Tax (C’)
Corporate tax (C)
Total
Summary of all the marginal and joint probabilities.

Primary Medium Total

interest R N W
P(C and R) P(C and N) P(C and W)
C P(C) = 0.60
= 0.18 = 0.35 = 0.07

P(C and R) P(C and N) P(C and W)

C P(C) = 0.40
= 0.17 = 0.10 = 0.13
Total P(R) = 0.35 P(N) = 0.45 P(W) = 0.20 1.00

* P(R) = P(C and R) + P(C and R)

* P(C) = P(C and R) + P(C and N) + P(C and W)

Find the probability that the caller

a) aware of the report through words of mouth

P(W) = 0.20 --- marginal probability (simple event)

b) is primarily interested in personal tax

P(C) = 1 – P(C) = 1 – 0.60 = 0.40

c) is primarily interested in corporate tax and became

aware of the report through the newspaper

P(C and N) = 0.35 --- joint probability (joint event)

d) became aware of the report through the radio or
newspaper

Since R & N are mutually exclusive events,

P(R or N) = P(R) + P(N) = 0.35 + 0.45 = 0.80

e) is primarily interested in corporate tax, or became

aware of the report through the radio or both

Since C & R are not mutually exclusive events,

P(C or R) = P(C) + P(R) – P(C and R)

= 0.60 + 0.35 – 0.18 = 0.77

 Conditional Probability
 Conditional probability measures the likelihood of
an event will occur, given that another event has
occurred.

Conditional probability of event A, given that event B

has occurred is

Conditional probability of event B, given that event A

has occurred is
 Multiplication Rule

 The multiplication rule is used to calculate the joint

probability of two events. It is based on the formula
for conditional probability.

 Multiplication Rule:

P(A and B) = P(A|B)  P(B)

Likewise, P(A and B) = P(B|A)  P(A)

 Independent Events
 Objective of calculating conditional probability is to
determine whether two events are independent.

 Independent events

The occurrence of one event has no effect on the

probability of the occurrence of any other event.

 Two events A and B are said to be independent if

P(A|B) = P(A) or P(B|A) = P(B)

 The Multiplication Rule for independent events

P(A and B) = P(A)  P(B)

Refer to Example 2
f) The probability that the caller became aware of
the report through the radio, given that he or she is
primarily interested in corporate tax

g) The probability that the caller is primarily interested in

personal tax, given that he or she became aware of
the report through the newspaper
h) Are C and N independent events?

If C & N are independent events, we must have either

P(C|N) = P(C) or P(N|C) = P(N)

From the contingency table,

P(C|N) = 0.778 ; P(C) = 0.60

P(C|N)  P(C), C and N are not independent events.

Since C and N are not independent events, the joint

probability of C and N, P(C and N) CANNOT be calculated
using the Multiplication Rule for independent events.
Therefore, P(C and N)  P(C) x P(N)
 Probability Trees

 The Multiplication Rule can be illustrated using a

probability tree. It is useful in visualizing events that
occur in sequence.

 The events in an experiment are represented by

lines. The resulting figure resembles a tree, hence
the name.

 At the ends of the “branches”, we calculate joint

probabilities as the product of the individual
probabilities on the preceding branches.
Probability Trees 0.3 R 0.18 P(C dan R)
=
│ C)
P (R
N 0.35 P(C dan N)
C P(N│C) = 0.583
0.6 P(
) = W
│C
C
P( )=
0.
11
7 W 0.07 P(C dan W)

P( . 425 R 0.17 P(C’ dan R)

C’ 0
)= C’) =
│
0. P (R
4
N 0.10 P(C’ dan N)
C’ P(N P(N│C’) = 0.25
│C
’) =
0.3
25 W 0.13 P(C’ dan W)
Example 3: Probability Trees
Law school grads must pass a bar exam. Suppose pass
rate for first-time test takers is 72%. They can re-write if
they fail and 88% pass their second attempt. What is the
probability that a randomly grad passes the bar?

P(Pass) = .72
First exam

= . 72
ss)
P(Pa Second exam
P(Fail and Pass)=
P( Fa ail) = .88 (.28)(.88)=.25
s|F
il) =
.28 P(Pas
P( Fa
il|Fail P(Fail and Fail) =
) = .12
(.28)(.12) = .03
Example
What is the probability that a randomly grad passes the bar?
“There is almost a 97% chance they will pass the bar”
P(Pass) = P(Pass 1st) + P(Fail 1st and Pass 2nd) =
= 0.7200 + 0.2464 = .9664

P(Pass) = .72
First exam

= . 72
ss)
P(Pa Second exam
P(Fail and Pass)=
P( Fa ail) = .88 (.28)(.88)=.25
s|F
il) =
.28 P(Pas
P( Fa
il|Fail P(Fail and Fail) =
) = .12
(.28)(.12) = .03
Example 4:
A standard certification test was given at three locations.
1,000 candidates took the test at location A, 600 candidates at
location B, and 400 candidates at location C. The percentages
of candidates from locations A, B, and C who passed the test
were 70%, 68%, and 77%, respectively. One candidate is
selected at random from among those who took the test.

a) What is the probability that the selected

candidate took the test at location B?

b) What is the probability that the selected

candidate passed the test if he or she took the test at
location A?

c) What is the probability that the selected

candidate took the test at location C and failed?
 Probability Tree for Example 4
(Dependent Events)
Marginal
probability a) P(B) = 0.30

b) P(P|A) = 0.70

c) P(C and P)

= P(C) x P(P|C)
= 0.20 x 0.23
= 0.046

Conditional
probability
 Bayes’ Law
 Bayes’ Law is a method of transforming the prior
probability of an event into a posterior probability
given that additional information is obtained.

 Prior probability

The initial prob. based on the present level of info.

 Posterior probability

A revised prob. based on additional information

 Bayes’ Law is an extension of the concept of

conditional probability
Refer to Example 4

d) If the selected candidate passed the test, what

is the probability that the candidate took the test
at location A, B and C respectively?

P(A) = 0.5 , P(B) = 0.3 , and P(C) = 0.2

are called prior probabilities because they are

determined prior to the results of the test

P(P|A) = 0.70 , P(P|B) = 0.68 , P(P|C) = 0.77

are the given conditional probabilities

Therefore, the conditional probability P(A|P) and similar
conditional probabilities, P(B|P) and P(C|P) are called
posterior probabilities or revised probabilities because the
prior probabilities are revised after obtaining the results of
the test.

The additional info. (results of the test) can be either

P : passed the test or P : failed the test

The prob. that a selected candidate passed the test is

P(P) = P(P and A) + P(P and B) + P(P and C)

= 0.35 + 0.204 + 0.154 = 0.708

The revised probability that the candidate took the test
at different location when the probability of passed the
test, P(P) is obtained can be calculated as follow

P( A and P) 0.35
P( A | P)    0.494
P(P) 0.708

P(B and P) 0.204

P(B | P)    0.288
P(P) 0.708

P(C and P) 0.154

P (C | P )    0.218
P(P) 0.708
Exercise:
Pay $500 for MBA prep??

The Graduate Management Admission Test (GMAT) is a requirement for all

applicants of MBA programs. There are a variety of preparatory courses
designed to help improve GMAT scores, which range from 200 to 800. Suppose
that a survey of MBA students reveals that among GMAT scorers above 650, 52%
took a preparatory course, whereas among GMAT scorers of less than 650 only
23% took a preparatory course.

An applicant to an MBA program has determined that he needs a score of more

than 650 to get into a certain MBA program, but he feels that his probability of
getting that high a score is quite low--10%. He is considering taking a
preparatory course that cost $500. He is willing to do so only if his probability
of achieving 650 or more doubles. What should he do?
Answer
Convert to Statistical Notation
Let A = GMAT score of 650 or more,
hence AC = GMAT score less than 650
Our student has determined the probability of getting
greater than 650 (without any prep course) as 10%, that
is:
P(A) = .10
It follows that P(AC) = 1 – .10 = .90

Let B represent the event “take the prep

course”
and thus,
Hence, BC is “do not take the prep course”
ANSWER
Conditional probabilities are
P(B | A) = .52
and
P(B |AC ) = .23

Again using the complement rule we find the following

conditional probabilities.
P(BC | A) = 1 -.52 = .48
and
P(BC | AC ) = 1 -.23 = .77
ANSWER
We are trying to determine P(A | B), perhaps the definition of
conditional probability from earlier will assist us…

We don’t know P(A and B) and we don’t know P(B). Hmm.

Perhaps if we construct a probability tree…

ANSWER:
In order to go from
P(B | A) = 0.52 to P(A | B) = ??
we need to apply Bayes’ Law. Graphically:

Score ≥ 650 Prep Test

B|A .52 A and B 0.052

0
A .1 B C|A .48 A and BC 0.048 Now we just
need P(B) !

B|A .23
C
AC AC and B 0.207
.90

B C|A C .77 AC and BC 0.693

ANSWER:
In order to go from
P(B | A) = 0.52 to P(A | B) = ??
we need to apply Bayes’ Law. Graphically:

Score ≥ 650 Prep Test

B|A .52 A and B 0.052

0 Marginal Prob.
A .1 B C|A .48 A and BC 0.048
P(B) = P(A and B) +
P(AC and B) = .259

B|A .23
C
AC AC and B 0.207
.90

B C|A C .77 AC and BC 0.693

ANSWER
Thus,

The probability of scoring 650 or better doubles to 20.1% when

the prep course is taken.
Exercise:

Ali has 2 motorcycles namely Honda and Suzuki. Usually,

75% of Ali's time is used to go to work on a Honda and the
rest on a Suzuki. If he use a Honda motorcycle, the
probability of Ali reaching earlier at work is 70%. But,
when using suzuki the probability is 0.6. This is because
suzuki motorcycles may have many problems.
Suppose one day Ali arrives late to work and gives the
excuse that his motorcycle has a problem, what is the
probability that he uses a Honda that day.