MGMT 322

Lecture Notes
1
 CHAPTER 2
Probability Types
and Related
Applications
2
Types of Events
• In statistics 2 events can be INDEPENDENT EVENTS or
DEPENDENT EVENTS.

• This is another important classification of events. Without a

good understanding of this topic we may not be able to
understand the computation of certain types of probabilities
such as Joint and Conditional Probabilities.

1. Statistically Independent Events

2. Statistically Dependent Events

3
1. STATISTICALLY INDEPENDENT EVENTS
• These are those (2) events whereby the probability of occurrence
of an event is not affected by (or not dependent upon) the
occurrence of the other event.

• Example 1
Events: A: Fatma goes to Istanbul next Tuesday
B: Istanbul stock market decreases by more than 10% next
Friday

• Example 2
Events: C: It rains in Argentina tomorrow.
D: Turkish Lira loses value against US dollar tomorrow.

• Events A and B are Independent events because the occurrence 4

of event “A” (logically) does not have an impact on the
probability of the occurrence of event “B”.
2. STATISTICALLY DEPENDENT EVENTS
• These are those 2 events whereby the probability of the
occurrence of an event is affected by (or dependent upon)
the occurrence of the other event.

• Example 1
Events: A: Stock Market Index rises tomorrow
B: Tomorrow Interest rates fall.

Therefore: Events A and B are Dependent Events because basic

finance theory suggests that the occurrence of event “B” is
expected to increase the probability of the event “A”

5
• Example 2
Events: A: The number of automobiles purchased in Turkey rises
next year
B: The quantity of petroleum consumed in Turkey rises
next year

Using our basic microeconomic background we can say that

Events A and B are Dependent events because the probability
of the occurrence of event “B” is affected by( or dependent
upon) the occurrence of event “A”.

Why? Because, the increased demand and use of automobiles in

Turkey is normally expected to increase the consumption of
petroleum. This means that probability of occurrence of event B
is affected by the occurrence of the event A. In other words, if 6
event A takes place the likelihood of the occurrence of event B
increases.
TYPES OF PROBABILITIES

• IN GENERAL WE HAVE 3 DIFFERENT TYPES OF PROBABILITIES;

1)MARGINAL PROBABILITY (also called UNCONDITIONAL

PROBABILITY)
2 ) JOINT PROBABILITY (of a group of events)
3) CONDITIONAL PROBABILITY( this is the probability of occurrence
of an event conditional upon the occurrence of another event)

• NOTE: CALCULATION OF JOINT AND CONDITIONAL

PROBABILITIES ARE DONE DIFFERENTLY FOR INDEPENDENT
AND DEPENDENT EVENTS.

7
TYPES OF PROBABILITIES UNDER INDEPENDENCE

• Assuming that EVENTS A and B are STATISTICALLY INDEPENDENT events:

1. Marginal (Unconditional) Probability

P(A): As we have seen before, in this case, we are interested in the
probability of the occurrence of only one event (unconditionally). And the
issue of Independence or Dependence does not matter here because we
have only one event in the context of the question.

2. Joint Probability
• P(AB): This is where you are interested in the probability of events A and
B happening together at the same time or in succession(one after
another).

P(AB) = P(A) * P(B)

P(BA) = P(B) * P(A) 8
A and B are independent events. .(NOTE: P(AB) = P(BA) )
3. Conditional Probability

• Conditional upon the occurrence of another event (B) what is the

probability of occurrence of an event (A)? Or alternatively it can be
expressed as ; If event B takes place what is the probability of
occurrence of event A? This is the conditional probability of A given
B and stated symbolically as follows;
P(A/B): Conditional Probability of A, given B!

• As long as A and B are independent events P(A) is not affected by

the occurrence of B and P(B) is not affected by the occurrence of
event A so;
P(A/B) = P(A) ( Conditional Prob.of A is equal to its marginal
probability)

• Similarly conditional probability of B given the occurrence of event 9

A is equal to its marginal probability as stated below;
P(B/A) = P(B)
• Example 1
Events : A: The weather is rainy in Cyprus today.
B: Exchange rate of dollar/yen increases today

A and B are Statistically Independent Events because logically

we don’t expect the occurrence of A to affect the probability of
occurrence of B and vice-versa.

Therefore: P(A/B) = P(A)

P(B/A) = P(B)

10
• Example 2

Suppose that we carry out the following 2 experiments in the

next 5 minutes;

Exp 1: Tossing a coin 3 times. And Exp.2: Rolling a die.

EVENTS;
A: GETTING AT LEAST 2 HEADS AS A RESULT OF EXP. 1.
B: GETTİNG A NUMBER GREATER THAN NUMBER 1 AS A RESULT
OF EXP.2

• FIRST DECIDE ABOUT WHETHER A and B are INDEPENDENT or

DEPENDENT EVENTS and then
• CALCULATE P(A) and P(B) , P(AB) , P(A/B) and P(B/A) 11
Q1: Obtain the marginal probabilities of A and B.( Which
approach you used?)
P(A)=4/8 and P(B)=5/6 ( We used CLASSICAL APPROACH)

Q2: Calculate the joint prob. of events A and B

P(AB)=4/8*5/6=20/48

Q3: Calculate the conditional prob. of A given that B takes

place.
=P(A/B)=4/8

Q4: Calculate the conditional prob. of B given that A takes

place.
=P(B/A)=5/6
12
TYPES OF PROBABILITIES UNDER DEPENDENCE

• Assuming that events A and B are DEPENDENT EVENTS:

1. Marginal (Unconditional) Probability

P(A) : As explained before, in this case, we are interested in the
probability of the occurrence of only one event unconditionally
(without any reference to any other event)

2. Joint Probability
We can see from the CONDITIONAL PROBABILITY FORMULAS GIVEN
BELOW that there are 2 ALTERNATIVE FORMULAS that can be used to
obtain joint probability of a given pair of events ( A and B);
P(AB) =P(A/B)*P(B)
P(BA)=P(B/A)*P(A)
13
• NOTE THAT P(AB)=P(BA) (Both of these notations represent joint
prob. of A and B)
3. Conditional Probability
P(A/B) = P(AB) / P(B) (Conditional Prob. of A given B)
P(B/A) = P(BA) / P(A) (Conditional Prob. of B given A)

• Note P(AB)=P(BA)

• Example
Suppose that the numerical distribution of students in terms of
eye color and sex in a class of 40 people is given as follows;

Black Green Total

Male 20 8 28
Female 10 2 12
Total 30 10 40

14
Experiment: Randomly selecting a student

Events:
A: Selecting a Male student.
B: Selecting a student with Black Eyes.
C: Selecting a Female student.
D: Selecting a student with Green Eyes

• Q1 If the selected student is a Male student what is the

probability that he has got Green eyes?
P(D/A) = P(DA) / P(A) = (8/40) / (28/40) = 0.286

• Q2. If the selected student is a Female student, what is the

probability that she has got Green Eyes.
15
P(D/C) = P(DC) / P(C) = (2/40) / (12/40) = 0.167
• The formula for conditional probability computation we used
above for DEPENDENT EVENTS is actually known as BAYES
THEOREM in statistics and is widely used in many disciplines
including management, finance and economics to obtain
relatively more accurate estimates of probabilities by
processing new information that we believe to be relevant for
the event that we are interested.

• The Theorem is explained in detail below.

16
Bayes’ Theorem
• Bayes’ Theorem is used for revising (updating) prior estimates of
probabilities (that we had estimated before the occurrence of a new
event )of the events that we are interested using limited new
information( in the form of occurrence of this new event) to obtain
posterior (new) probabilities that are hopefully more accurate estimates
relative to our initial (prior) estimates.

• Suppose that we are interested in obtaining the PROBABILITY OF

OCCURRENCE of Event A and using an appropriate approach we
estimated P(A). This marginal probability of A is known (in the context of
Bayes Theorem) as prior probability of A. After sometime passes, event
B occurs and we believe that these 2 events are dependent events.

• In this context this means that we believe that the occurrence of event 17
B has changed the probability of occurrence of A.
• We can use Bayes Theorem to obtain posterior (new prob)
probability of A in the sense that it is obtained after the
occurrence of B.
P (A/B) = P (AB)/ P(B)

18
• Example 1
Suppose we have 100 dice in a basket, and we have two types;
half of them are Type1 and the other half are Type2. The
probability of getting Ace (1) when you roll a Type1 die is 0.3 and
the probability of getting Ace (1) when you roll a Type 2 die is
0.6. Assume that you have randomly selected a die from this
basket and rolled it and you found out that Ace (1) has come up.
Given this result, what is the probability of this die to be a Type1
die?

We can understand from the question that ; These two events

(Ace and Type1) (or Ace and Type 2) are dependent events
because the probability of getting Ace(1) is affected by the
occurrence of Type1 or Type 2 die.

P( Type1/Ace) = P(Type1 Ace) / P(Ace) 19

 Note: When you are not given the values for the formula like in
the example above, use the following five steps below in order
to get the Answer:

Step 1: First identify ELEMENTARY EVENTS and the SECONDARY

EVENT of the question.

In this case the elementary events are TYPE1 andTYPE2. And

the secondary event is the new information given to us which is
the occurrence of ACE(1). In other words whatever the question
is asking us that event is one of the ELEMENTARY EVENTS. And
we automatically understand what the other elementary
events are.

20
 Step 2: Prepare the following table:
Conditional Probability of Secondary
Marginal Probability of Elementary
Secondary Event Event, Given Each of the Elementary
Events
Event

P(Type 1) = 0.5 P(Ace / Type 1) = 0.3

ACE
P(Type 2) = 0.5 P(Ace / Type 2) = 0.6

Step 3: Obtain the MARGINAL probability of the secondary

event.

P(secondary event) = summation of the individual joint probabilities of the

secondary event with each one of the elementary events.

P(Ace) = P(Type1, Ace) + P( Type2, Ace)

21
Step 4: Compute the joint probability of the secondary event
with each one of the elementary events and add them up to get
P(secondaryevent)

P(Type 1, Ace) = P(Ace/Type1)* P(Type 1)

= 0.3 * 0.5 = 0.15

P(Type 2, Ace) = P(Ace/Type2) * P(Type2)

= 0.6 * 0.5 = 0.30

P(Ace) = 0.15 + 0.30 = 0.45

This 0.45 is the probability of getting Ace (1) when you roll a
randomly selected die from this basket.
22
Step 5: Apply Bayes Theorem by using the joint probabilities you
obtained in step 4 to get the final answer.

P(Type1/ Ace) = P(Type 1, Ace) / P(Ace)

= 0.15 / 0.45 = 1/3 This is posterior
probability (ANSWER)

23
• Example 2
Economists believe that the annual inflation rate in Turkey is
affected by the changes in the petroleum prices. The probability
of inflation rate increasing in 2021 is estimated to be 0.60. The
probability of petroleum prices rising in 2021 is estimated as
0.40. The probability of both inflation rate and the petroleum
prices rising in 2021 is given as 0.35. On the other hand, the
probability of inflation rate rising and at the same time, the
petroleum prices not rising in 2021 is estimated to be 0.20. If
petroleum prices do not rise in 2021, what is the probability of
inflation rate rising in 2021?

Events: I: Inflation rate increasing in 2021.

P: Petroleum prices rising in 2021.
N: Petroleum prices not rising in 2021. 24
Question is P(I/N) = ?
Given data in the question:
P(I) = 0.6
P(P) = 0.4
P(IP) = 0.35
P(IN) = 0.2

Solution:
P(N) = 1 – P(P) = 1- 0.4 = 0.6
P(I / N) = P(IN) / P(N) = 0.2 / 0.6 = 0.333

25
• Example3
Annual profits of construction sector depend on wage rate paid
to labor employed by the sector. The past data about the
behavior of annual profits suggests that the probability of profits
rising in a given year is 0.80 and the probability of profits falling
is 0.20. The past data also suggests that in 60% of all the years
during which the profits have increased, wage rate has declined,
and it has increased in the remaining 40%. However, in 80% of
all years during which profits have fallen, wage rate has
increased, and only in the remaining 20% wage rate has
decreased. Due to the economic crisis in Turkey, wage rate has
been declining since the beginning of 2020. Given this
downward trend in wages, what is your revised estimate for the
probability of annual profits of construction sector to rise in this
year?

26
Events: A: Profits rising
B: Profits falling
C: Wage rate declining
D: Wage rate increasing

IN THIS QUESTION THE ELEMENTARY EVENTS ARE A and B. And the

SECONDARY EVENT is C. So the QUESTION is what is P(A/C)

Given:
P(A) = 0.80
P(B) = 0.20

And we can estimate the following conditional probabilities using the

relative frequency approach.
P(C/A) = 0.60
P(D/A) = 0.40
27
P(D/B) = 0.80
P(C/B) = 0.20
Note that P(C/A) and P(C/B) are the CONDITIONAL PROBABILITIES OF THE
SECONDARY EVENT GIVEN EACH ONE OF THE ELEMENTARY EVENTS.

In step by step solution that we have shown in the first example we have to
place these conditional probabilities in the last column of the TABLE that is
prepared in Step 2.

You attempt to solve this question using the step by step solution method. In
what follows the solution has been provided without going through these steps
in detail.

P(C/A) = P(CA) / P(A) ( REMEMBER P(AC)=P(CA) )

0.60 = P(CA) / 0.80 and therefore;

P(CA) or P(AC) = P(C/A) * P(A) = 0.60 * 0.80 = 0.48

Similarly P(BC) = P(C/B) * P(B) = 0.20*0.20= 0.04

P(C) = P(AC) + P(BC)
= [P(C/A) * P(A)] + [P(C/B) * P(B)] 28
= (0.60 * 0.80) + (0.20 * 0.20)
P(C) = 0.48 + 0.04 = 0.52
P(A/C) = P(AC) / P(C) = 0.48 / 0.52 = 0.92 ANSWER

Given the fact that wages have been declining in Turkey since
the beginning of this year the probability of the profits of
construction sector to increase this year has been revised to
92%. But initially in the beginning of the year (before the decline
in wages) our prior estimate was 80%.

29
• Example 4
A child chosen at random in a community school system comes
from low-income family 15% of the time. Children from low-
income families in the community graduate from college
(university) only 20% of the time. Children not from low-income
families have a 40% chance of graduating from college. As an
employer of people from this community, you have been
reviewing applicants and noted that the first one had a college
degree. What is the probability that this person comes from a
low-income family?

Events: L: Child coming from a low-income family

G: Graduate from college
H: Child not coming from a low-income family

The question is P(L/G)=? 30

(From the information given in the question that are listed
below we can understand that these 2 events , L and G, are
DEPENDENT events .Therefore we need to apply Bayes Theorem
to get the answer)

Note that in this question L and H are ELEMENTARY EVENTS and

G is the SECONDARY EVENT.

Given:
P(L) = 0.15
P(H) = 1- P(L) = 1- 0.15 = 0.85
P(G/L) = 0.20
P(G/H) = 0.40
P(L/G) = ?
31
Solution:
P(L/G) = P(LG) / P(G)
P(L/G) = (P(G/L) * P(L)) / P(G)
P(G) = P(LG) + P(HG)

P(G) = [P(G/L) * P(L)] + [P(G/H) * P(H)]

= (0.20 * 0.15) + (0.40 * 0.85)
= 0.03 + 0.34 = 0.37

P(L/G) = 0.03 / 0.37 = 0.08 = 8%

• Note: To find the marginal probability of THE SECONDARY

EVENT , you need to add up all of its joint probabilities with
each one of the ELEMENTARY EVENTS.
32
• Example 5
A new diagnostic test to detect CORONA VIRUS has been
introduced into FAMAGUSTA Hospital. The manufacturer of the
test device has determined that the probability of a false-
positive reading (a positive test result for a person who is known
not to have virus) is 8%. The probability of a false- negative
reading (a negative reading for a person who has the virus) is
4%. Turkish Cypriot health authorities estimate that
approximately 15% of the population in the town has the virus.
If a test is conducted on a patient from Famagusta and the test
result is positive what is the probability that the corona virus is
really present in that person?

33
Solution: FIRST ATTEMPT TO SOLVE THIS QUESTION USING THE
STEP BY STEP SOLUTION METHODOLOGY YOURSELF.

Events:
H: A randomly selected person is healthy (he does not have the
virus)
I: A randomly selected person is ill. (he has the virus)
P: A positive test result (test result suggests that he has the virus)
N: A negative test.result (test result suggests that he does not have
the virus)

We have the following information;

P(P/H)= 0.08
P(N/I)=0.04
P(I)=0.15
P(H)=1- P(I)=1- 0.15= 0.85 P(H)=0.85 34
P(I/P)=P(IP)/P(P)
 • Step 1: Elementary Events are I and H. Secondary event is the
test result which is positive (P)

• Step 2:
Conditional probability of
Marginal Probability of
Secondary Event secondary event given
elementary events
each elementary event.
P(H)=0.85 P(P/H)=0.08
P
P(I)=0.15 P(P/I)=? 0.96

Note the following to understand how we obtained the values in

the TABLE above.
P(N/I)= 0.04
Using this information we can get P(P/I) as follows:
P(P/I)= 1- P(N/I)
P(P/I)= 1- 0.04= 0.96
35
• Step 3: Computation of the probability of secondary event.
P (P) = P(HP) + P(IP)

• Step 4: Computation of joint probability of the secondary

event with each one of the elementary events.
P(HP)= P(P/H) x P(H) P(HP)= 0.08 x 0.85= 0.068

P(IP)= P(P/I) x P(I) P(IP)= 0.96 x 0.15= 0.144

Step 5: P(P)= P(HP)+ P(IP) P(P)= 0.068 + 0.144= 0.212

36
Step 6: Use the Bayes’ Theorem to get the final answer.

P (I/P) = P (IP) / P (P) = 0.144/ 0.212 = 0.679= 67.9%

Therefore given that the test result for this person is positive the
new probability of this person actually having the corona virus is
67.9%. But remember our prior estimate for the same
probability (before finding out the test result) was only 15%
which was the marginal prob. of the event I given by the
percentage of the population who are assumed to have the
virus.

37