Analytics and Quantitative

Techniques
Introduction to Probability Theory
Introduction to Probability Theory
• Welcome to the Probability Theory lecture.
• Today, we will cover:
• Basic Probability Concepts
• Conditional Probability and Independence
• Bayes' Theorem
• We will also look at some real-world business examples to
illustrate these concepts.
 Sources of Uncertainty
• Information is partial
• Information is not fully reliable.
• Representation language is inherently imprecise.
• Information comes from multiple sources, and it is
conflicting.
• Information is approximate
• Non-absolute cause-effect relationships exist
• Probability theory enables us to make rational
decisions.
Basic Probability Concepts
• Probability: It is a measure of the likelihood that an event will occur. It is quantified as a
number between 0 and 1, where 0 indicates impossibility and 1 indicates certainty.
• Experiment: Any process that generates well-defined outcomes.
• Sample Space (S): The set of all possible outcomes.
• Event: A subset of the sample space.
• Probability of an Event (P(E)): Number of favourable outcomes divided by the total number
of possible outcomes.
• Formula:

• Example:
• Tossing a fair coin.
• Sample Space, S = {Heads, Tails}
• Probability of getting Heads, P(Heads) = 1/2 = 0.5
Sample Space (S)
• The sample space is the set of all possible outcomes of a random
experiment.
• Example: In a business context, consider a company launching a new
product. The possible customer responses (sample space) could be:

• S = {Very Satisfied, Satisfied, Neutral, Dissatisfied, Very Dissatisfied}

• Event (E)
• An event is a subset of the sample space. It is a single outcome or a set
of outcomes from the sample space.
• Example: An event could be "customers who are satisfied or very
satisfied.“

• E = {Very Satisfied, Satisfied}

Probability of an Event (P(E))
• Example
• 100 attempts are made to swim a length in 30 secs. The swimmer succeeds on 20
occasions therefore the probability that a swimmer can complete the length in 30 secs is:
• 20/100 = 0.2
• Failure = 1 - 0.2 or 0.8

• The experiments, the sample space and the events must be defined clearly for
probability to be meaningful
• What is the probability of an accident?

• Principle of Indifference—Alternatives are always to be judged equiprobable if

we have no reason to expect or prefer one over the other.
• Each outcome in the sample space is assigned equal
probability.
Axioms of Probability Theory
• Probability theory provides a mathematical framework for
quantifying uncertainty and making predictions about future
events based on known data.
• The foundation of this framework is built upon three fundamental
axioms, formulated by the Russian mathematician Andrey
Kolmogorov in 1933.
• These axioms form the basis of modern probability theory and are
essential for understanding and applying probabilistic concepts.
Non-negativity Axiom
• The first axiom states that the probability of any event is a non-negative
number.

• Consider a standard six-sided die. The probability of rolling any specific

number (1 through 6) is always a non-negative value. For instance, the
probability of rolling a 3 is:

• This value is clearly non-negative.

Normalization Axiom
• The second axiom states that the probability of the sample space
(the set of all possible outcomes) is equal to 1.

• For the six-sided die, the sample space S is {1, 2, 3, 4, 5, 6}. The
sum of the probabilities of all possible outcomes must equal 1.
Additivity Axiom
• The third axiom states that if two events, A and B, are mutually
exclusive (they cannot happen at the same time), then the probability
of either A or B occurring is the sum of their individual probabilities.

• Continuing with the six-sided die, consider the events A = rolling a 2

and B = rolling a 5. These two events are mutually exclusive because
the die cannot show both 2 and 5 at the same time.

• Since A and B are mutually exclusive:

Real-World Examples
• Weather Forecasting
• Weather forecasts rely heavily on probability theory to predict the likelihood of various
weather conditions. For example, the probability that it will rain tomorrow might be given as
70%. This means that, based on current data and models, there is a 70% chance of rain and
a 30% chance of no rain, adhering to the normalization axiom.
• Medical Testing
• In medical testing, probabilities are used to determine the likelihood of a patient having a
particular disease based on test results. If a test is 95% accurate, this means the probability
of the test correctly identifying the disease (true positive) or correctly identifying its absence
(true negative) is high, adhering to the non-negativity axiom.
• Finance
• In finance, probability theory is used to assess the risk of investment portfolios. For example,
the probability of a stock's return being above a certain level or the risk of a financial loss is
often calculated. If two events, such as the return on two different stocks, are independent,
the additivity axiom helps in calculating the combined probability of both events occurring.
Probability of an Event (P(E))
• The probability of an event is the ratio of the number of favourable outcomes to the total
number of possible outcomes.

• Example:
• If a survey shows the following responses:
• Very Satisfied: 30
• Satisfied: 40
• Neutral: 20
• Dissatisfied: 5
• Very Dissatisfied: 5
• Total responses = 100
• The probability of a customer being satisfied or very satisfied is:
Complementary Events (E')
• The complement of an event E is the set of all outcomes in the
sample space that are not in E.

• ( ′) = 1− ( )

• Example:
• The probability of a customer not being satisfied or very satisfied:
• (Not Satisfied or Very Satisfied) = 1− (Satisfied or Very Satisfied)
• = 1−0.70 = 0.30
Conditional Probability (P(A|B))
• The probability of event A occurring given that event B has occurred.

• Example:
• Assume we have data on customers who bought a product and their
satisfaction levels:
• Customers who bought: 80
• Of these, customers who are satisfied: 50
• The probability that a customer is satisfied given that they bought the product:
Independence
• Independence: Two events A and B are independent if the occurrence of one does
not affect the probability of the other.
• Formula for Independence:

• Example:
• Drawing cards from a deck.
• Event A: Drawing an Ace.
• Event B: Drawing a Spade.
• Sample Space: 52 cards.
• P(A) = 4/52 = 1/13.
• P(B) = 13/52 = 1/4.
• If independent, P(A ∩ B) = P(A) × P(B) = 1/13 × 1/4 = 1/52.
Independence…
• Independence: Two events A and B are independent if the occurrence
of one does not affect the probability of the other.
• Formula for Independence:

• Example:
• Consider two independent events:
• Event A: Customer is from Zomba city (P(A) = 0.3)
• Event B: Customer is satisfied (P(B) = 0.6)
• The probability that a customer is from Zomba city and is satisfied:
Mutually Exclusive Events
• Two events are mutually exclusive if they cannot occur at the
same time.
• ( )= ( )+ ( )
• Example:
• Consider two mutually exclusive events:
• Event A: Customer is dissatisfied (P(A) = 0.1)
• Event B: Customer is very dissatisfied (P(B) = 0.05)
• The probability that a customer is either dissatisfied or very dissatisfied:

( ) = ( ) + ( ) = 0.1 + 0.05 = 0.15

Bayes' Theorem
• Bayes' Theorem: A way to update the probability of a hypothesis based on new evidence.
• Formula:

• Useful in various business scenarios like spam detection, medical diagnosis, etc.
• Example:
• Diagnostic testing for a disease.
• Event A: Person has the disease.
• Event B: Test is positive.
• Given:
• P(A) = 0.01 (1% prevalence).
• P(B|A) = 0.99 (99% sensitivity).
• P(B|¬A) = 0.05 (5% false positive rate).
• Calculation:
 Real-World Applications in Business
• Probability theory is crucial in decision-making processes in business.
• Examples include risk assessment, marketing campaign success evaluation, and customer behaviour prediction.
• Case Study:
• Scenario: Evaluating the probability of a marketing campaign's success based on historical data.
• Historical data shows:
• 60% of campaigns have been successful (P(Success) = 0.60).
• 70% of successful campaigns had high engagement (P(High Engagement|Success) = 0.70).
• 30% of unsuccessful campaigns had high engagement (P(High Engagement|¬Success) = 0.30).
• New campaign has high engagement.
• Calculation:
• Objective: Find P(Success|High Engagement).
• Use Bayes' Theorem:

Result: There is a 77.78% probability that the campaign will be successful given high engagement.
 Conditional Probability Calculation
• Scenario: Determining the likelihood of customer purchase behaviour using
conditional probability.
• Historical data:
• 40% of customers purchase (P(Purchase) = 0.40).
• 70% of customers who viewed the product page made a purchase (P(Purchase|View) =
0.70).
• 50% of all customers viewed the product page (P(View) = 0.50).
• Calculation:
• Objective: Find P(View|Purchase).
• Use Bayes' Theorem:

Result: There is an 87.5% probability that a customer viewed the product page given that they made a purchase.
Conditional Probability - Quality Control
• In a factory, there are two machines, A and B, producing widgets.
Machine A produces 60% of the widgets, and Machine B produces
40%. The probability of a widget being defective from Machine A is
2%, and from Machine B is 3%.
• We want to find the probability that a randomly selected defective
widget came from Machine A.
1.Let D be the event
that a widget is
defective.
2.Let A be the event
that a widget came
from Machine A.
3.Let B be the event
that a widget came
from Machine B.
We need to find P(A D)
Quality Control in Manufacturing
• Suppose a factory produces 1,000 widgets a day. Out of these, 5%
are defective. A quality control test can detect defective widgets
with a 98% accuracy, and correctly identifies non-defective
widgets 97% of the time.
Let's denote:
•D as the event that a widget is
defective.
•T as the event that the test
indicates a defect.
Given:
•P(D)=0.05
•P(T D)=0.98
•P(T ¬D)=0.03
•P(¬D)=0.95
We want to find P(D T), the
probability that a widget is
defective given that it tested as
defective.
 Business Students
Of 100 students completing a course, 20 were
business major. Ten students received As in the
course, and three of these were business majors.,
suppose A is the event that a randomly selected
student got an A in the course, B is the event that a
randomly selected event is a business major. What is
the probability of A? What is the probability of A after
knowing B is true?
B not B

A 80
3 7

20
Dataset for Marketing Campaign
Success:
Campaign ID Engagement Level Success (1=Yes, 0=No)
1 High 1
2 Low 0
3 High 1
4 High 0
5 Low 0
6 High 1
7 Low 1
8 High 0
9 High 1
10 Low 0
Dataset for Customer Purchase
Behaviour
Customer ID Viewed Product Page (1=Yes, 0=No) Made Purchase (1=Yes, 0=No)
1 1 1
2 0 0
3 1 1
4 0 0
5 1 0
6 1 1
7 0 0
8 1 1
9 1 0
10 0 0
Conclusion
• Summary of key points:
• Basic probability concepts.
• Importance of conditional probability, complementary, independence
and mutually exclusive events.
• Application of Bayes' Theorem in real-world scenarios.
• Practical examples demonstrating the use of probability theory in
business.
• It is important to understand and apply these concepts to make
informed business decisions.
• You are encouraged to practice with real-world data to solidify
your understanding.