Quantitative

Business Analysis
Basic Probability

The University of Sydney Page 1

 Learning
Objectives

In this chapter, you learn:

– Basic probability concepts

– Various counting rules
– Conditional probability
– To use Bayes’ Theorem to revise
probabilities

Page
2
Areas Analytics are most often used

– New customer acquisition

– Measuring and boosting customer
loyalty
– Pricing tolerance
– Cross-sell / up-sell / targeted
advertisements
– Supply, staffing optimization
– Financial forecasting
– Fraud detection
– Product placement
– Churn measurement and reduction
Page
3

Explicitly predict probabilities of events

Probability used to make business decisions
Churn management “safety nets”

– http://www.youtube.com/watch?v=ukM2AdNJq0I

Page
4
Basic Probability
Concepts
Basic Probability
Concepts

– Probability – the chance that an uncertain event will occur (always

between 0 and 1)

– Impossible Event – an event that has no chance of occurring

(probability = 0)

– Certain Event – an event that is sure to occur (probability = 1)

Page
6
Assessing Probability

An example of three approaches to assess the probability

of an uncertain (discrete or category) event:

1. a priori -- based on prior knowledge of the

process probability of occurrence = X = number of ways the event can occur
T total number of outcomes

2. empirical probability -- based on observed

data number of ways the event has occurred
= number of trials
probability of occurrence
3. subjective probability
Probability of occurrence is based on a combination of an individual’s
past experience, personal opinion, and/or analysis of a particular situation
Page
7
 Events

Each possible outcome of a variable is called an event.

– Simple event
– described by a single characteristic
– e.g., A customer purchases a product
– Joint event
– An event described by two or more characteristics
– e.g. A customer purchases a product and pays more than $100
– Complement of an event A (denoted A’)
– All events that are not part of event A
– e.g., the customer does not purchase the product Page 8

– E.g. the customer pays $100 or more, or pays less than $100
Sample Space

The collection of all possible events

different, mutually
e.g. All 6 faces of a die: exclusive and collectively
exhaustive

e.g. All 52 cards in a deck:

e.g. a customer purchases (“Yes”)

OR does not purchase (“No”) the product

Page 9
Joint Probability, Marginal
Probability, and General
Addition Rule
 Visualizing Events

– Contingency Tables -- For All Customers

Purchase Not Sub-total

purchase
>$100 4 48 52
<=$100 27 286 313
Sub-Total 31 334 365

4 Sample size
Decision Trees 0
0
>$ 1
Sample as e <=1 27
Space All purch 00
customers 100
Not >$ 48
purch <=1
ase
00 286 Page
16
 Definition: Marginal (Simple) Probability

refers to the probability of a simple event.

– ex. P(Purchase a specific product)
– ex. P(willing to pay > $100)
P(willing to pay> $100)
Purchase Not Sub-total = 52 / 365
purchase
>$100 4 48 52
<=$100 27 286 313
Sub-Total 31 334 365

P(Purchase) = 31 / 365 Page

17
 Definition: Joint Probability

– refers to the probability of an occurrence of

two or more events (joint event).
– ex. P( Purchase & paid > $100 )
– ex. P( Not Purchase & paid < $100 )
Purchase Not Sub-total
purchase
P(Not Purchase & paid < willing to pay
>$100 4 48 52
$100)
<=$100 27 286 313 = 286 / 365
Sub-Total 31 334 365
P( Purchase & willing to pay > $100) = 4 / 365 Page
13
Mutually Exclusive Events

– Mutually exclusive events

– Events that cannot occur simultaneously

Example: Randomly choosing a day from 2018

– Events A and B are mutually exclusive

A = day in January; B = day in February

Page
14
Collectively Exhaustive Events
– Collectively exhaustive events
– One of the events must occur
– The set of events covers the entire sample space

Example: Randomly choose a day from 2018

A = Weekday; B = Weekend; C = January; D = Spring;

– Events A, B, C and D are collectively exhaustive (but not

mutually exclusive – a weekday can be in January or in
Spring) Page
– Events A and B are collectively exhaustive and also 15
mutually exclusive
Computing Joint and Marginal Probabilities

– The empirical probability of a joint event, A and B:

number of outcomes satisfying A and B

P(A and B) =
total number of elementary outcomes

– Computing a marginal (or simple) probability:

• Where B1, B2, …, Bk are k mutually exclusive
P(A) = P(Aand
andcollectively
B ) + P(A exhaustive
1
and B ) +!+events
2
P(A and B ) k

Page
16
 Marginal & Joint Probabilities
In A Contingency Table

Event
Event B1 B2 Total
A1 P(A1 and B1) P(A1 and B2) P(A1)
A2 P(A2 and B1) P(A2 and B2) P(A2)

Total P(B1) P(B2) 1

Joint Probabilities Marginal (Simple) Probabilities

Page
17
Probability Summary So Far

– Probability is the numerical

measure of the likelihood that an 1 Certain
event will occur
– The probability of any event must
be between
0 ≤ P(A)0 and
≤ 1 1, For any event A
– The sum of the probabilities of 0.5
all mutually exclusive and
collectively exhaustive events
is 1
P(A) + P(B) + P(C) = 1
0 Impossible
If A, B, and C are mutually exclusive and
collectively exhaustive Page
25
 General Addition Rule

General Addition Rule:

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

If A and B are mutually a, then

P(A and B) = 0, so the rule can be simplified:

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

For mutually exclusive events A and B Page
19
 General Addition Rule
Example
P(Purch. OR willing to pay >$100) = P(Purch.) + P(>$100) - P(Purch.&>$100)

= 31/365 + 52/365 - 4/365 = 79/365

Don’t count the 4

Purchase Not Sub-total purchases with
purchase spend > $100
twice!
>$100 4 48 52
<=$100 27 286 313
Sub-Total 31 334 365

Page
20
Conditional Probability
Computing Conditional Probabilities

– A conditional probability is the probability of one

event, given that another event has occurred:

The conditional
P(A and B)
P(A | B) = P(B) probability of A given that
B has occurred

The conditional
probability of B given
P(A and B)
P(B | A) = that A has occurred

P(A)

Where P(A and B) = joint probability of A and B

Page
P(A) = marginal or simple probability of A 31

P(B) = marginal or simple probability of B

E.g. Conditional Probability
that:
– A customer will buy book B after buying book A (e.g.
Amazon)

– A customer will “click-through” based on a particular web

page design (e.g. Bing)

– An asset price will go up following a positive earnings

result

– A customer “churns” following a “customer interaction

event” by a company.

– A customer actually purchases

P(A and B) =after
P(Aanswering
| B) × P(B) a survey Page
question saying they “plan to purchase” (page 173 text) 32
 Conditional Probability
Example =
P(>$100 | purchase) = P(>$100 and purchase) 4/365
31/365
P(purchase)
= 4/31 = 0.129

Purchase Not Purchase Total

> $100 4 48 52
≤ $10027 286 313
Total 31 334 365

Page
33
Conditional Probability Example

■ Of the cars on a used car lot, 90% have air

conditioning (AC) and 40% have a GPS. 35% of
the cars have both.

– What is the probability that a car has a GPS

given that it has AC ?

i.e., we want to find P(GPS | AC)

Page
25
Multiplication Rules

– Multiplication rule for two events A and B:

P(A and B) =P(A | B)P(B)

Note: If A and B are independent, then

P(A | B) =
P(A)
and the multiplication rule simplifies to

P(A and B) = P(A)P(B) Page

26
 Bayes’ Theorem

– Bayes’ Theorem is used to revise previously calculated

probabilities based on new information.

– Developed by the Reverend Thomas Bayes in the 18th Century.

– It is an extension of conditional probability.

– It allows us to usefully reverse the conditioning

between two events or variables.
Page
27
Bayes’
Theorem

P(A | B i)P(B
P(Bi | A)
P(A | B1)P(B 1) + P(A
i
) | B )P(B ) + ⋅⋅⋅ + P(A | B
= 2 2 k
)P(B k )

– where:
Bi = ith event of k mutually exclusive and collectively
exhaustive events

A = new event that might impact i

NB P(B | A) = P(A and B)
P(A)
P(B )
Page
28
Questions?

The University of Page

Sydney 66