Analysis of a multiple objective decision is to calculate the expected value or create the risk
profile for each individual objective. Lets do this analysis for our summer job example.
Analysis: Salar
Dominance
Using expected value to compare different risky prospects is useful but EMV can sometimes
inadequately captures the nature of the risks that must be compared. With risk profiles, we can
make
The linked tree is shown above with all the formulas included in the calculations.
Example 2:
Making Decisions with Multiple Objectives
So far we have only focused on a single-objective decision. How
We can create a tree like the one shown below.
To link the tree Click the root cell Mail Order and under Calculation tab, change the method
to Linked Spreadsheet and make it Automatic update. Link the
Click on both the chance nodes and link them to the cell containing the $10.00 which is the
shipping fee (cell B4). Make sure you repeat the process for the other chance node.
Note that for all possible values of x:
Pr(Outcome x| Firm B)
Pr(Outcome x| Firm A)
or equivalently:
Pr(Outcome x| Firm B)
Pr(Outcome x| Firm A)
Hence the chances of winning with Firm B are always b
one risk profile over another. Dominance is used to help us identify those profiles and their
associated strategies that can be ignored. Such strategies are said to be dominated because we
can use som
The next step is to decompose problems in order to understand their structures and measure
uncertainty and value. Decomposition is the key to decision analysis. The approach used is
divide and conquer
understand the relationships among multiple objectives. We will assess utility functions in order
to model the way in which decision maker value different outcomes and trade off competing
objectives.
No we need to compare each alternative based on the lowest level in your hierarchy of decision
criteria.
-Commute time
-Safety
-Access to Java Jolt
-Access to Cuppa Jo
-Route A is somewhat faster than
Lets revisit the definitions of Decision Path and Strategy that we just went through not long ago.
Decision Path:
A path starting at the left most node up to the values at the end of a branch by selec
back to Banana for $30 per share anytime within the next year (during which time it will become
known whether EYF succeeds or fails.)
Questions:
1. Calculate Steves expected value for the deal. Ignore
Building group creativity is very important for successful organizations and several formal
methods are outlined below.
1) Brainstorming
Brainstorming is very important in group creativity. This is wh
Case Study: Southern Electronics, Part I
Steve Sheffler is president, CEO, and majority stockholder of Southern Electronics, a small firm
in the town of Silicone Mountain. Steve faces a major decision
STEP 1: Fundamental and Means Objectives
Objectives can be classified as means or fundamental. Fundamental objectives are what the
decision-maker really wants to accomplish. These are the basis by whi
Sometimes we may have to use attribute scale to measure our objectives. For example, how does
one measure quality? One solution is to define an attribute scale: BEST, BETTER,
SATISFACTORY, WORSE, WORS
Some of the questions that need to be considered in classifying objectives are summarized in
following table (page 52 in the textbook). It is important to note that Decision Problems are
evaluated usi
To calculate the weights of individual criteria add the individual columns and divide each
element by the total in the corresponding column and average them across each row,
This weighted score sugges
Min Max Regret Approach
This is neither optimistic nor conservative, but somewhere in the middle. In this case, we create a
regret table, as follows. If the state of nature is s1, the best payoff will
2.2 Structuring Decisions
In this chapter, we are going to talk about how to structure objectives and building influence
diagrams and decision tress. Understanding ones objective in a decision context
expected value with perfect information, we use these payoff values and the original probabilities
to obtain expected value with perfect information.
The expected value for the decision with perfect i
Lesson 2: Modeling Decisions I
2.1 Introduction
Before we start chapter 3, please read the next few pages in which I try to explain the decision
making processes various people use and some very simpl
if successful, will revolutionize the industry. Southern Electronics could play an important role
in the development of the machine.
In their discussions, several important points have surfaced. First
opinion, Leonardo da Vinci is the greatest creator the world has even seen. He was a scientist,
mathematician, engineer, inventor, anatomist, painter, sculptor, architect, botanist, musician, and
writ
Identify your first level of evaluation criteria.
-Commute time
-Safety
-Drive-through access (to coffee)
Decide if there are second level criteria, or sub-criteria of these, related to any of your
Le
o
o
o
Number of people exposed to the chemical per day?
Ingesting a critical quantity?
Skin contact?
The decision maker must try to find answers to these questions before the decision model can be
use
filing for bankruptcy. The reason for the simplifications is because our purpose is to represent
only the main issues in the problem for our analysis in this lecture.
Given tough negotiation positions