Statistics

Chapter 4: Basic Probability Concepts

Many business decisions are made under conditions of uncertainty. Probability theory
provides the foundation for quantifying and measuring uncertainty.

A probability is the chance, or likelihood, that a particular event will occur.

E.g. probability-type questions:

• What is the probability/chance that it will rain today?
• What is the likelihood that a task will be completed within 45 minutes?
• How likely is it that a product will fail within its guarantee period?

1. TYPES OF PROBABILITY
⇒ 2 Types of probability:
1. Subjective probability – cannot be statistically verified and is not used much for
statistical analysis
2. Objective probability – when probability of an event occurring can be verified
statistically through surveys or empirical observations; used extensively.

r
Any probability is defined as: P(A) =
n

Where: A = event of a specific type (or with specific properties)

r = number of outcomes of event A
n = total number of all possible outcomes (sample space)
P(A) = probability of event A occurring

E.g. Assume 355 Ford car owners (n = 355) were randomly selected and asked: ‘When
you buy your next car, will you buy another Ford product?’ (event A). 76 respondents
said ‘yes’. (r = 76)
76
Then: P(A) = = 0.214 (21.4%)
355

⇒ 3 ways in which objective probabilities can be derived:

1. a priori
2. empirically
3. mathematically

2. PROPERTIES OF A PROBABILITY
There are 5 basic properties that apply to every probability:
1. a probability value lies only between 0 and 1 inclusive (0 ≤ P(A) ≤ 1)
2. if an even cannot occur: P(A) = 0
3. if an event is certain to occur: P(A) = 1
4. the sum of probabilities of all possible events (collectively exhaustive set of
events) = 1 [P(A1) + P(A2) + . . . P(Ak) = 1] for k number of events
5. Complementary probability: If P(A) is the probability of event A occurring, then
the probability of event A not occurring, is: P(Ā ) = 1 – P(A)

3. BASIC PROBABILITY CONCEPTS

170 companies from JSE were randomly selected and classified by sector and size. The
following cross-tabulation table of joint frequencies for two categorical random
variables ‘sector’ and ‘company size’ are given.
1
 Sector Company size Row Total
Small Medium Large
Mining 3 8 30 41
Financial 9 21 42 72
Service 10 6 8 24
Retail 14 13 6 33
Column Total 36 48 86 170

⇒ Look at examples for concepts, p.110-113

Concept 1: Intersection of two events (A ∩ B)
⇒ set of all outcomes that belong to both A and B simultaneously. Keyword is ‘and’

Concept 2: Union of two events (A ∪ B)

⇒ set of all outcomes that belong to either event A or B or both. Keyword is ‘or’

Concept 3: Mutually exclusive events

⇒ events are mutually exclusive if they cannot occur together on a single trial of a
random experiment

Concept 4: Collectively exhaustive events

⇒ union of all possible events is equal to the sample space; probability = 1

Concept 5: Statistically independent events

⇒ two events, A and B, are statistically independent if the occurrence of event A has no
effect on the outcome of event B, and vice versa

4. CALCULATING OBJECTIVE PROBABILITIES

⇒ Look at examples p. 113-115

Marginal probabilities P(A)

⇒ probability of a single event A occurring only → P(A)

Joint probability P(A ∩ B)

⇒ probability that both event A and B will occur simultaneously on a single trial of a
random experiment

Conditional probability (PA/B)

⇒ probability of event A occurring, given that event B has already occurred

P ( A ∩B)
P(A/B) =
P( B)
5. PROBABILITY RULES
⇒ to calculate probabilities of compound or multiple events:
• The addition rule
- for mutually exclusive events
- for non-mutually exclusive events
• The multiplication rule
- for statistically dependent events
- for statistically independent events

2
170 companies from JSE were randomly selected and classified by sector and size. The
following cross-tabulation table of joint frequencies for two categorical random
variables ‘sector’ and ‘company size’ are given.

Sector Company size Row Total

Small Medium Large
Mining 3 8 30 41
Financial 9 21 42 72
Service 10 6 8 24
Retail 14 13 6 33
Column Total 36 48 86 170

Addition rule for mutually exclusive events

⋇ What is the probability that a randomly selected JSE-listed company is either a mining
company or a service company?

41
⇒ let A = event (mining company) =
170
24
⇒ let B = event (service company) =
170

⟡Note that the keyword here is ‘or’ – meaning that addition rule will be applicable
⟡Find whether events A and B are mutually exclusive or not (can occur simultaneously
or not); in this case: no, they cannot occur simultaneously (they are mutually
exclusive)

Use formula:
P(A ∪ B) = P(A) + P(B)

41 24 65
P(Mining ∪ Service) = + = = 0.38 (38%)
170 170 170

Addition rule for non-mutually exclusive events

⋇ What is the probability that a randomly selected JSE-listed company is either a large
company or a financial company, or both?

86
⇒ let A = event (large company) =
170
72
⇒ let B = event (financial company) =
170

⟡Note that the keyword here is ‘or’ – meaning that addition rule will be applicable
⟡Find whether events A and B are mutually exclusive or not (can occur simultaneously
or not); in this case: yes, they can occur simultaneously (they are non-mutually
exclusive); large and financial can cross in the table
Use formula:
P(A ∪ B) = P(A) + P(B) – P(A ∩ B)

3
 42
P(A ∩ B) is where both events (large and financial) occur/cross in table =
170

86 72 42 116
P(Large ∪ Financial) = + – = = 0.68 (68%)
170 170 170 170

Multiplication rule for statistically dependent events

⇒ used to find joint probability of events A and B

P(A ∩ B) = P(A/B) ⨯ P(B)

⋇ What is the probability of selecting a small retail company?

⇒ let A = event (small company)

⇒ let B = event (retail company)

⟡ the keyword here is ‘and’

⟡ the probability is where the two events cross in the table
⟡ not necessary to do all the steps for formula (see example p.119)

14
P(Small ∩ Retail) = = 0.082 (8.2%)
170

Multiplication rule for statistically independent events

⇒ if two events A and B are statistically independent (i.e. there is no association
between the two events) then the multiplication rule reduces to the product of
the two marginal probabilities only:
P(A∩B) = P(A) × P(B)

Not applicable on cross-tabulation table (see p. 119)

Example of conditional probability

⋇ What is the probability that a randomly selected company is a retail company, given
that it is known (in advance) to be a medium-sized company?

⇒ let A = event (retail company)

⇒ let B = event (medium company)
Use formula:
P ( A ∩B)
P(A/B) =
P( B)

13
P ( Retail ∩ Medium) 170 13
P(Retail/Medium) = = = = 0.271
P(Medium) 48 48
170
(27.1%)

6. COUNTING RULES – PERMUTATIONS & COMBINATIONS

⇒ 3 basic counting rules:

4
• Multiplication rule of counting
- For single event: total number of different ways in which n objects can be
arranged, is given by n!.
e.g. In a 6-lane swimming pool, how many unique arrangements of 6 swimmers
can be considered?
Answer: 6! = 6 ⨯ 5 ⨯ 4 ⨯ 3 ⨯ 2 ⨯ 1 = 720
- For combined events: particular random process has n1 possible outcomes for
event 1, n2 possible outcomes for event 2, . . . nj possible outcomes for event j,
then the total number of possible outcomes for j events collectively is:
n1 ⨯ n2 ⨯ n3 . . . ⨯ nj
e.g. A restaurant menu has a choice of 4 starters, 10 main courses and 6 desserts.
What is the total number of possible unique meals that can be ordered?
Answer: n1 = 4; n2 = 10; n3 = 6, thus 4 ⨯ 10 ⨯ 6 = 240 possible meals

• Permutation rule
⇒ a permutation is the number of distinct ways of selecting (or arranging) a subset of r
objects drawn from a larger group of n objects, where the order of selection of objects
is important
n!
nPr =
( n−r ) !
Where: r = number of objects selected at a time
n = total number of objects from which to select
- E.g. A factory has 3 machines and 8 possible machine operators. How many
distinct assignments (orderings) of machine operators are possible?
- Answer: r = 3; n = 8
8!
8P3 = = 336 permutations
( 8−3 ) !

• Combinations rule
⇒ a combination is the number of distinct ways of selecting (or arranging) a subset of
r objects drawn from a larger group of n objects where the order of selection of
objects is not important
n!
nCr =
r ! ( n−r ) !

- E.g. A company produces fruit juice in 10 different flavours. A local supermarket

sells the product, but has only sufficient shelf space to display 3 of the 10 fruit
juice flavours at a time. How many possible groupings (combinations) of 3
flavours can the fruit juice company display on the shelf?
- Answer: r = 3; n = 10; order in which the 3 juice flavours are displayed, is not
10 !
important 10C3 = = 120 combinations
3! (10−3 ) !

_________________________________________________________________________