Module 4 Probability: An introduction to modeling

uncertainty (Part 1)

Lecturer: Dr Wendy Shi

Maritime and Logistics Management

F96, Swanson Building

Wenming.Shi@utas.edu.au
 Key topics in this module

• Events and probabilities

• Basic relationships of probability

• Conditional probability

• Random variables
Uncertainty
 Uncertainty and probability

• Uncertainty is an ever-present fact of life for decision makers. Much time and effort are

spent trying to plan for and respond to uncertainty.

 In many business scenarios, data are available to provide information on possible outcomes for some

decisions, but the exact outcome from a given decision is almost never known with certainty because

many factors are outside the control of the decision maker (e.g., actions taken by competitors, the

weather).

• Probability is the numerical measure of the likelihood that an event will occur.

 This measure of uncertainty is often communicated through a probability distribution.

 It can provide additional information about an event and help a decision maker evaluate possible

actions and determine best course of action.

Events and probabilities
 Random experiment

• A random experiment is a process that generates well-defined outcomes.

 Sample space: all possible outcomes

 Event: a collection of outcomes

 Probability of an event: it is equal to the sum of probabilities of outcomes for the event.

• Example: rolling a die

 Possible outcomes are defined as “the number of dots showing on the upward face of the die”.

 Sample space; Events: A= the observed number is smaller than 3; Probability: P(A)? P(B)?

B= the observed number is greater than 4

Relationships of probability
 Completion of an event

• The complement of an event A (AC) is defined to be the event consisting of all outcomes

that are not in A.

• Venn diagram

 Rectangular area: the sample space for the random experiment and contains all possible outcomes.

 Circle: event A and contains only the outcomes that belong to A

 Shaded region: it contains all outcomes not in event A.

Relationships of probability
• P(A) can be computed easily if the probability of its complement is known.

 Addition law

• Applicability: The addition law is helpful when we are interested in knowing the

probability that at least one of two events will occur. It is related to the combination of

events (i.e., union, intersection).

• Union of events ( A  B. ): The event containing all outcomes belonging to A or B or both.

Relationships of probability
• Intersection of events ( A  B.): it contains the outcomes that belong to both A and B.

 Area in which the two circles overlap is the intersection. It contains outcomes that are in both A and B.

• Mutually exclusive events

 If the occurrence of one event precludes the occurrence of the other.

 If the events have no outcomes in common

Conditional probability
 Conditional probability

• When the probability of one event (A) is dependent on whether some related event (B)

has already occurred. It is written P(A|B).

 The notation | indicates that we are considering the probability of event A given the condition that event

B has occurred. Hence, the notation P(A|B) reads “the probability of A given B.”

• Illustration: Lancaster Savings and Loan

 Interested in mortgage default risk.

 Interested in whether the probability of a customer defaulting differs by marital status.

Conditional probability
• Crosstabulation
Conditional probability
 The probability that a customer

defaults on his or her mortgage is:

120/300=0.4

 The probability that a customer does

not default on his or her mortgage is:

1-0.4=0.6 or 180/300

 Question: Is this probability different

for married customers as compared

with single customers?

Conditional probability

 What is the probability that a randomly selected customer does not default on his or her mortgage and

the customer is married? P(M∩D)=79/300=0.2633 .

 P(M∩DC)=64/300=0.2133 is the probability that a randomly selected customer is married, and that the

customer does not default on his or her mortgage.

 P(S∩D)=41/300=0.1367 is the probability that a randomly selected customer is single and that the

customer defaults on his or her mortgage.

 P(S∩DC)=116/300=0.3867 is the probability that a randomly selected customer is single and that the

customer does not default on his or her mortgage.

Conditional probability
• Joint probabilities: When values give the probability of the intersection of two events

• Marginal probabilities: They are found by summing the joint probabilities in the corresponding row or

column of the joint probability table.

• Conditional probabilities can be computed as the ratio of joint probability to a marginal probability.

 P(D|M)=P(D∩M)/P(M)=0.2633/0.4766=0.5524; Note also that the conditional probability P(D|M) can be

computed as the ratio of the joint probability P(D∩M) to the marginal probability P(M).
Conditional probability
• Excel PivotTable to calculate conditional probabilities

 We can calculate these conditional probabilities by right-clicking on any numerical value in the body of

the PivotTable and then selecting Show Values As and choosing % of Row Total.
Conditional probability
• Independent events

 If the probability of event D is not changed by the existence of event M, then we would say that events

D and M are independent events. Otherwise, the events are dependent.

• Multiplication law

 To calculate the probability of the intersection of two events.

Conditional probability
• Bayes’ theorem

 Logic: 1) begin the analysis with initial or prior probability estimates for specific events. 2) obtain

additional information about events. 3) given new information, update the prior probability values by

calculating revised probabilities, referred to as posterior probabilities.

 Example: consider a manufacturing firm that receives shipments of parts from two different suppliers.

A1=the event that the part is from supplier 1; A2=the event that a part is from supplier 2.

G=the event that a part is good; B=the event that a part is bad.

Prior probabilities: P(A1)=0.65; P(A2)=0.35

The quality (G, B) of the purchased parts varies according to their source.

 Question: Given the information that the part is bad, what is the probability that it came from supplier

1 and what is the probability that it came from supplier 2?

Conditional probability
Conditional probability

• Bayes’ theorem is applicable when events for which we want to compute posterior probabilities are

mutually exclusive and their union is the entire sample space.

Random variables
 Random variable

• It is a numerical description of the outcome of a random experiment. They are quantities

whose values are not known with certainty.

 Discrete random variable (DRV): it can take on only specified discrete values.

 Continuous random variable (CRV): it may assume any numerical value in an interval or collection of

intervals (e.g., time, weight, distance, and temperature).

 Many DRVs have a large number of potential outcomes and so can be effectively modeled as CRVs.
Discrete probability distributions
Thanks for your attention!