IIMT 2641 Introduction to Business Analytics

Module 1: Probability
Xiao Lei
Objectives
1. Understand key probability definitions.

2. Understand and apply probability concepts: intersection, union, complement, and

mutually exclusive using tables, trees, formulas and Venn diagrams.

3. Understand and solve conditional probability problems using tables, trees, Venn
diagrams and formulas

4. Define independence of events, and use the independence assumption to solve

problems.

2
Basic probability concepts
▪ Experiment: is a process that produces a single outcome whose result cannot be predicted with
certainty

▪ Outcomes of an experiment are the events that might possibly happen

– There are two possible outcomes when flipping a coin: "heads" and "tails"
– There are 52 possible outcomes when picking a card at random from a deck

▪ An event is a collection of outcomes

– "The card picked is a spade"
– "The card picked is a seven"
– "The card picked is a jack, queen, or king”

▪ Sample Space: is the set of all possible outcomes of an experiment

– Example: Sample space of a single die toss:

S={ } or S = {1,2,3,4,5,6}

3
Basic probability concepts

▪ Probability is a numerical statement about the

likelihood that an event will occur

▪ Notation: P(A) = Probability of event A

▪ Two basic rules of probability
▪ 0 ≤ 𝑃 𝐴 ≤ 1.
▪ The sum of the simple probabilities for all
possible outcomes of an activity (experiment)
must equal 1.

4
Basic probability concepts

5
Today’s Objectives
1. Understand key probability definitions.

2. Understand and apply probability concepts: intersection, union, complement, and

mutually exclusive using formulas and Venn diagrams.

3. Understand and solve conditional probability problems using tables, trees, Venn
diagrams and formulas

4. Define independence of events, and use the independence assumption to solve

problems.

6
Venn Diagram Representations of Probability
Sample Space

Event A Event B

Sample Space

Event A Event B

7
Venn Diagram Representations of Probability
Sample Space

Rolling a Rolling a
3 2

Rolling a 1, 4, 5, or 6

Sample Space

Rolling a
Rolling
number
an even
greater
number
than 3

Rolling a number 3 or smaller that is not even (i.e., Rolling a 1 or 3)

8
“A intersection B”: aka A ∩ B
“A intersection B” (A ∩ B) indicates the set of outcomes that are common
to both A and B
Sample Space

Event A Event B

“A intersection B” or A∩B or “A and B”

A = watching 1 to 7 movies per month

B = watching 4 or more movies per month
A ∩ B = watching 4 – 7 movies per month

9
“A union B”: aka A ∪ B
“A union B” (aka, A∪B) indicates the collection of outcomes that are in A or B.

Sample Space

Event A Event B

“A union B” or A ∪ B or “A or B”

A = watching 1 to 7 movies per month

B = watching 4 or more movies per month
A ∪ B = watching 1 or more movies per month

10
“A complement”: aka 𝑨′ or 𝑨𝒄
Sample Space

Event A Event B

A’ or “not A” or
“A complement”

P(A’) + P(A) = 1

11
Venn Diagram Representations of Probability
Sample Space

Event A Event B

12
Venn Diagram Representations of Probability
Sample Space

Event A Event B

A and B not B and not A

or A ∩ B or A’ ∩ B’

A and not B B and not A

or A ∩ B’ or A’ ∩ B

13
In Class Practice: Tea/Coffee
A study by Coffee Academics revealed 40% of undergraduates drink both coffee and tea. The study
also found 70% of undergraduates drink coffee. No students reported drinking neither coffee nor tea.
P(Coffee ∩ Tea) = 0.4 P(Coffee) = 0.7 P(Coffee’∩Tea’) = 0

1. What is the probability a randomly chosen undergraduate drinks coffee but not tea?

P(Coffee ∩ Tea’) = 0.3

2. What is the probability a randomly chosen

Coffee Tea
undergraduate drinks tea?
P(Tea) = 0.4 + 0.3 = 0.7 0.3 0.4 0.3

3. What is the probability a randomly chosen

undergraduate drinks tea but not coffee? 0

P(Coffee’ ∩ Tea) = 0.3

14
Mutually Exclusive
Mutually Exclusive
– Two events are mutually exclusive if they cannot occur at the same time
– A and B are mutually exclusive if their intersection is the empty set.
𝐴∩𝐵 = ∅

– Example:
❑ A = rolling a pair of dice and getting at least one 2
❑ B = rolling a pair of dice and getting a sum of 12

If A and B are Mutually Exclusive , then P(A or B) = P(A) + P(B).

15
Collectively Exhaustive
A set of events are said to be collectively exhaustive if at least one of them must
occur.

If A and B are collectively exhaustive, then P(A or B) = 1.

Example:
❑ A = rolling a dice and getting at least 3

❑ B = rolling a dice and getting at most 4

16
In-class Exercises

Mutually Collectively
Two events: A and B Exclusive Exhaustive
1. Draw a spade and a club
2. Draw a face card and a number card
3. Draw an ace and a 3
4. Draw a club and a non-club
5. Draw a 5 and a diamond
6. Draw a red card and a non-diamond

17
In-class Exercises

Mutually Collectively
Two events: A and B Exclusive Exhaustive
1. Draw a spade and a club Yes No
2. Draw a face card and a number card Yes Yes
3. Draw an ace and a 3 Yes No

4. Draw a club and a non-club Yes Yes

5. Draw a 5 and a diamond No No

6. Draw a red card and a non-diamond No Yes

18
Useful Probability Rules

▪ Rule 1: The probability of any event is a number

between zero and one: 0 ≤ P(A) ≤ 1.

▪ Rule 2: Additive rule for probability of union of two

events
𝑃 𝐴 ∪ 𝐵 = 𝑃 𝐴 + 𝑃 𝐵 − 𝑃(𝐴 ∩ 𝐵)

▪ Rule 3: (Law of Total Probability): For any two

events A and B, we have
𝑃 𝐴 = 𝑃 𝐴 ∩ 𝐵 + 𝑃(𝐴 ∩ 𝐵′)

We are utilizing the property that B and B’ are mutually exclusive and
collectively exhaustive!
19
Today’s Objectives
1. Understand key probability definitions.

2. Understand and apply probability concepts: intersection, union, complement, and

mutually exclusive using formulas and Venn diagrams.

3. Understand and solve conditional probability problems using tables, trees, Venn
diagrams and formulas

4. Define independence of events, and use the independence assumption to solve

problems.

20
Conditional Probability
Conditional Probability: Probability of “A given B” = P(A|B)
▪ The probability of A, given that B has already happened.
▪ The probability of A, given that we are “in” B.
▪ The probability of A, given we know B is true.
Additional (new) information allows us to re-assess the likelihood of the event.
Probability may change.
Prior Probability
This is our initial assessment of the likelihood of A
Number of times 𝐴 occurs
𝑃 𝐴 = Example: A: the card picked is a Queen
Number of trials
Conditional
Probability This is our updated assessment of the likelihood of A
after observing that B occurred.
𝑃 𝐴𝐵 Example: B: the card picked is a face card
21
Conditional Probability
Conditional Probability: Probability of A given B = P(A|B)

What is the correct way to say P(A|B)?

Probability of:
• “A given B”
• “A conditional on B”

Our new population (Sample Space) is restricted to “B”

and we are interested in the likelihood that A occurs
within this new population.

22
Conditional Probability Formula

Percentage of cases both 𝐴 and 𝐵 occur 𝑃(𝐴 ∩ 𝐵)

𝑃 𝐴𝐵 = =
Percentage of cases 𝐵 occurs 𝑃(𝐵)

Sample Space
𝑷(𝑨 ∩ 𝑩) B B’

A 𝑷(𝑨 ∩ 𝑩)
Event A Event B

A’ 𝑷(𝑨′ ∩ 𝑩)

𝑷 𝑨 ∩ 𝑩 + 𝑷 𝑨′ ∩ 𝑩 = 𝑷(𝑩)
23
Conditional Probability Formula

Let A denote "the card picked is the queen of any suit"

and B denote "the card picked is a face card", then

4/52
𝑃 𝐴𝐵 = = 1/3
12/52

24
A Property of Conditional Probability
Because conditional probability is focusing on the sub-space where the
event has occurred, the following property holds:

1 = 𝑃 𝐴 𝐵 + 𝑃 𝐴′ 𝐵

Sample Space
B B’

A
Event A Event B
A’

25
Coffee and Tea, Revisited
A study by Campus Coffee revealed 40% of undergraduates drink both coffee and tea. The study also
found 70% of undergraduates drink coffee. No students reported drinking neither coffee nor tea.
Coffee Coffee’
Coffee Tea
Tea .40 .30 .70
0.3 0.4 0.3
Tea’ .30 0 .30

0 .70 .30

1. Given a person drinks coffee, what is the probability they drink tea?
𝑃 𝑇𝑒𝑎|𝐶𝑜𝑓𝑓𝑒𝑒 = 0.4/0.7 = 0.57
2. What percentage of undergraduates drink tea but not coffee?
𝑃 𝑇𝑒𝑎 ∩ 𝐶𝑜𝑓𝑓𝑒𝑒′ = 0.3 or 30%
3. If a friend (an undergraduate) of yours does not drink tea, what is the probability they do drink
coffee?
𝑃 𝐶𝑜𝑓𝑓𝑒𝑒|𝑇𝑒𝑎′ = 0.3/0.3 = 1
26
Using Venn diagrams and tables
Sample Space
B B’

P(A)=P(A ∩ B)
Event A Event B A A∩ B A ∩ B’ +P(A ∩ B’)
P(A’)=P(A’∩ B)
A’ A’ ∩ B A’ ∩ B’ +P(A’∩ B’)

P(B)=P(A ∩ B) P(B’)=P(A ∩ B’)

+P(A’ ∩ B) +P(A’ ∩ B’)
A∩ B
A ∩ B’ A’ ∩ B’
A’ ∩ B

Can use these to compute conditional probability.

Can use conditional probability to compute these.

27
A Tale of Two Suppliers, Opposite Conditional
BYD uses machine parts from two suppliers (supplier G in Guangzhou and supplier D in
Dongguan), and occasionally receives bad parts due to machine breakdowns. BYD gets
60% of the parts from supplier G and 40% of the parts from supplier D. It is known 3.8%
of parts are bad overall. And it is known for a randomly selected bad part, there is a
79% chance it is from supplier G.
Given that a part is from Supplier G, what is the probability it is bad?
𝑃(𝐺) = 0.6 𝑭𝒊𝒏𝒅: 𝑷 𝑩𝒂𝒅 𝑮
𝑃(𝐺∩𝐵𝑎𝑑) ?
𝑃(𝐷) = 0.4 𝑃 𝐵𝑎𝑑 𝐺 = =
𝑃(𝐺) 0.6

𝑃(𝐵𝑎𝑑) = 0.038

𝑃(𝐺|𝐵𝑎𝑑) = 0.79

28
A Tale of Two Suppliers, Opposite Conditional
Given that a part is from Supplier G, what is the probability it is bad?

𝑃 𝐵 𝐴 𝑃(𝐴) 𝑷(𝑨 ∩ 𝑩) 𝑃 𝐵𝑎𝑑 𝐺 =

𝑃(𝐺∩𝐵𝑎𝑑)
=
?
𝑷 𝑨𝑩 = = 𝑃(𝐺) 0.6
𝑃(𝐵) 𝑷(𝑩)

We can find a formula for intersection:

𝑷(𝑨 ∩ 𝑩) = 𝑷 𝑨 𝑩 ∗ 𝑷(𝑩) We can now apply a formula for intersection:
𝑃(𝐺∩𝐵𝑎𝑑) 𝑃(𝐺|𝐵𝑎𝑑)𝑃(𝐵𝑎𝑑)
𝑃 𝐵𝑎𝑑 𝐺 = =
𝑃(𝐺) 0.6

0.79∗0.038
𝑃 𝐵𝑎𝑑 𝐺 =
0.6

𝑃 𝐵𝑎𝑑 𝐺 = 0.05

29
Bayes’ Rule
For two events: A and B

𝑃 𝐵 𝐴 𝑃(𝐴) 𝑃(𝐴 ∩ 𝐵) This formula helps you find P(A|B)

𝑃 𝐴𝐵 = =
𝑃(𝐵) 𝑃(𝐵) when you’re not given P(A ∩ B).

𝑃(𝐴 ∩ 𝐵) 𝑃(𝐴 ∩ 𝐵) 𝑃(𝐴 ∩ 𝐵)

𝑃 𝐴𝐵 = = =
𝑃(𝐵) 𝑃 𝐵 ∩ 𝐴 + 𝑃(𝐵 ∩ 𝐴′ ) 𝑃 𝐵 𝐴 𝑃 𝐴 + 𝑃 𝐵 𝐴′ 𝑃(𝐴′ )

𝑃(𝐴 ∩ 𝐵) 𝑃 𝐵 𝐴 𝑃(𝐴) 𝑃 𝐵 𝐴 𝑃(𝐴)

𝑃 𝐴𝐵 = = =
𝑃(𝐵) 𝑃 𝐵 ∩ 𝐴 + 𝑃(𝐵 ∩ 𝐴′ ) 𝑃 𝐵 𝐴 𝑃 𝐴 + 𝑃 𝐵 𝐴′ 𝑃(𝐴′ )

These formulas help you find P(A|B) when you’re not given P(A ∩ B) or P(B).

30
Bayes’ Theorem
▪ How to revise your probability assessment when you have new information?
▪ Bayes’ Theorem is used to incorporate additional information as it is made
available and help create revised or posterior probabilities from the original or
prior probabilities.

▪ Example
Prior Probability Rolling a 3
(Conditional)
Fair dice 0.5 0.166
Loaded dice 0.5 0.600

▪ Toss once and get a 3

▪ Revised P(the dice rolled was fair) = ?

31
Bayes’ Theorem

𝑃 𝐴𝐵 𝑃 𝐵|𝐴 𝑃 𝐴 𝑃 𝐵|𝐴 𝑃 𝐴
▪ 𝑃 𝐴|𝐵 = = =
𝑃 𝐵 𝑃 𝐵𝐴 +𝑃 𝐵𝐴′ 𝑃 𝐵|𝐴 𝑃 𝐴 +𝑃 𝐵|𝐴′ 𝑃 𝐴′

▪ 𝑃 fair dice|3 rolled = ?

▪ 𝑃 loaded dice|3 rolled = ?

32
Covid Testing
 Covid tests aim to confirm or rule out COVID-19 infection
in people with or without COVID-19 symptoms.
 PCR tests – laboratory test, 24 hours.
 Rapid Antigen tests – 15 minutes.

33
Covid Testing
 Base Rate for Covid
 P(Covid) = 0.2
 Covid test is positive (+) or negative (-)
 PCR tests typically have variable sensitivities and high
specificities. Consider the following situation:
 Test performance statistics
 Sensitivity: P(Positive | Covid) = 0.90
 Specificity: P(Negative | Not Covid) = 0.95
 Sensitivity and Specificity values are based on controlled
experiments.
 P(Covid | Positive) = ?

34
Covid Testing
▪ Draw a tree here to find joint probabilities
𝑃 𝐶 ∩ + = 0.2*0.9
0.9 + = 0.18

Covid (C)
0.2
𝑃 𝐶 ∩ − = 0.2*0.1
0.1 - = 0.02

𝑃 𝐶 ′ ∩ + = 0.8*0.05
0.05 + = 0.04
0.8
Not (C’)

0.95 𝑃 𝐶 ′ ∩ − = 0.8*0.95
- = 0.76

35
Covid testing
1. What proportion of patients do not have Covid and test negative?
𝑃 𝐶 ′ ∩ − = 0.8*0.95 = 0.76

2. What proportion of patients have Covid and test negative?

𝑃 𝐶 ∩ − = 0.2*0.1 = 0.02

3. What proportion of patients test negative?

𝑃 − = 𝑃 𝐶 ∩ − + 𝑃 𝐶 ′ ∩ − = 0.2*0.1 + 0.8*0.95 = 0.78

4. What proportion of patients test positive?

𝑃 + = 1.00 − 𝑃 − = 0.22

36
Covid testing
▪ Fill the table that contains P(C∩+), P(C∩-), P(C’∩+),
P(C’∩-), P(+), P(-), P(C), P(C’)

Positive (+) Negative (-)

Covid (C) 0.18 0.02 P(C) = 0.20

0.04 0.76
Not Covid (C’) P(C’) = 0.80

P(+) = 0.22 P(-) = 0.78 1.00

37
Covid testing
▪ Find posterior probabilities P(C|+), P(C’|+) , P(C|-) , P(C’|-)
using your table

Positive (+) Negative (-)

Covid (C) 0.18 0.02 P(C) = 0.20

0.04 0.76
Not Covid (C’) P(C’) = 0.80

P(+) = 0.22 P(-) = 0.78 1.00

P(C|+) = 0.18/0.22 = 0.82 P(C|-) = 0.02/0.78 = 0.03

P(C’|+) = 1.00-0.82 = 0.18 P(C’|-) = 1.00-0.03 = 0.97

38
Monty Hall Problem
In the 1970s, there was a game show called “Let’s Make a Deal” and Monty
Hall was the host. At some point in the game, contestants were asked to pick
one of three doors. Behind one door there was a car; behind the others,
goats. After the contestant picked a door, before revealing whether the
chosen door contained a car, Monty Hall would open one of the two
remaining doors and show the contestant there was no car behind that door.
Then he would ask “Do you want to switch doors?” What would you do?

39
Monty Hall Problem
▪ Suppose the door you pick initially is Door 1
▪ Let 𝐴 = Door 1 has a car behind it and 𝐵 Monty reveals a goat door
▪ The probability of winning a car by not switching is 𝑃(𝐴|𝐵)
▪ To use Bayes’ theorem, we break down the formula:
– 𝑃 𝐴 is the probability that Door 1 has a car behind it before Monty
reveals a door, which is 1/3.
– 𝑃 𝐴𝑐 is the probability that Door 1 has a goat behind it before Monty
reveals a door, which is 2/3.
– 𝑃(𝐵|𝐴) is the probability that Monty reveals a goat door, given that
Door 1 has a car behind it, which is 1 because Monty always reveals a
goat door
– 𝑃(𝐵|𝐴𝑐 ) is the probability that Monty reveals a goat door, given that
Door 1 has a car behind it, which is 1 because, again, Monty always
reveals a goat door
▪ We now apply Bayes’ theorem: 𝑃 𝐴 𝐵 =
▪ Hence, the probability of winning a car by switching is .
40
Monty Hall Problem
▪ Suppose the door you pick initially is Door 1
▪ Let 𝐴 = Door 1 has a car behind it and 𝐵 =
Monty reveals a goat door
▪ The probability of winning a car by not switching is 𝑃(𝐴|𝐵)
▪ To use Bayes’ theorem, we break down the formula:
– 𝑃 𝐴 is the probability that Door 1 has a car behind it before Monty
reveals a door, which is 1/3.
– 𝑃 𝐴𝑐 is the probability that Door 1 has a goat behind it before Monty
reveals a door, which is 2/3.
– 𝑃(𝐵|𝐴) is the probability that Monty reveals a goat door, given that
Door 1 has a car behind it, which is 1 because Monty always reveals a
goat door
– 𝑃(𝐵|𝐴𝑐 ) is the probability that Monty reveals a goat door, given that
Door 1 has a car behind it, which is 1 because, again, Monty always
reveals a goat door
𝑃 𝐵𝐴 𝑃(𝐴)
▪ We now apply Bayes’ theorem: 𝑃 𝐴 𝐵 = = 1/3
𝑃𝐵 𝐴 𝑃 𝐴 +𝑃 𝐵 𝐴𝑐 𝑃(𝐴𝑐 )
▪ Hence, the probability of winning a car by switching is 1- 1/3 = 2/3. 41
Monty Hall Problem (Some intuitive explanations)
Suppose the door you pick initially is Door 1
There's a 1/3 chance you get a car, and a 2/3 chance you get a goat.

If you chose a goat If chose the car first

If you choose a car first (1/3 chance) and then switch, you'll always get a goat. And,
if you choose a goat first (2/3 chance) and then switch, you'll always get the car.
This is why switching is the better option.

Therefore, if you stay, you'll get a 1/3 chance of getting the car, but if you
switch you'll have a 2/3 chance of getting the car.

42
Today’s Objectives
1. Understand key probability definitions.

2. Understand and apply probability concepts: intersection, union, complement, and

mutually exclusive using formulas and Venn diagrams.

3. Understand and solve conditional probability problems using tables, trees, Venn
diagrams and formulas

4. Define independence of events, and use the independence assumption to solve

problems.

43
Independence: The Concept
▪ Two events are independent if the occurrence of one event has
no effect on the probability that the other event occurs.
0.5 Heads

Heads
0.5
0.5 Tails

0.5 Heads
0.5
Tails

0.5 Tails

44
Independence: The Concept
▪ Two events are NOT independent if the occurrence of one event has an
effect on the probability that the other event occurs.
▪ Assume we have a drawer with 2 blue socks and 1 red sock, and we pick a
sock twice without replacement. 1/2 Blue Sock

Blue Sock
2/3
1/2 Red Sock

2/2 Blue Sock

1/3
Red Sock

0/2 Red Sock 45

Independence: The Math
For P(A)>0 and P(B)>0, A and B are independent, if and only if one of the following is
true:
P(A  B)
P(A | B) = = P(A)
P(B)
P(A  B)
P(B | A) = = P(B)
P(A)
P(A  B) = P(A)P(B)

If one of these is true, then the other two are also true.
How do I use these formulas?
1. The problem says “Assume A and B are independent”, then you are
allowed to use these formulas. If a problem does not say that, these
formulas are invalid. Do not use them.

2. The problem says “Are A and B independent?”, then you can check to see
if these formulas hold true. You only need to show one formula is true.
46
Independence Example
Example 1: It is known P(A) = 0.1 and P(B) = 0.4. It is also
known A and B are independent events. What is P(A∩B)?
Since A and B are independent, then P(A)*P(B) = P(A∩B).
So, P(A∩B) = 0.04.

Example 2: It is known P(A|B) = 0.5. It is also known A and B

are independent events. What is P(A)?

Since A and B are independent, then P(A|B) = P(A).

So, P(A) = 0.5.

47
Independence Example
Example 3: Two dice (red and blue) are rolled.
A = The sum is exactly 7. P(A) = 6/36
B = The sum is exactly 12. P(B) = 1/36

C = The red die rolled a 6. P(C) = 6/36

Are A and C independent? (Check if P(A)*P(C) = P(A∩C))

P(A)*P(C) = (6/36)*(6/36) = 1/36 YES,

A and C are
independent
P(A ∩ C) = P(red 6 and sum is 7) = P(6,1) = 1/36

Are B and C independent? (Check if P(B)*P(C) = P(B∩C))

P(B)*P(C) = (1/36)*(6/36) = 1/216 NO,

B and C are not
P(B ∩ C) = red 6 and sum is 12 = 1/36 independent

48
Today’s Objectives
1. Understand key probability definitions.

2. Understand and apply probability concepts: intersection, union, complement, and

mutually exclusive using formulas and Venn diagrams.

3. Understand and solve conditional probability problems using tables, trees, Venn
diagrams and formulas

4. Define independence of events, and use the independence assumption to solve

problems.

49