0% found this document useful (0 votes)
112 views79 pages

2 Modeling Tools For Decision Analysis

The document discusses two modeling tools for decision analysis: decision tables and decision trees. It provides details on the components and characteristics of each. Decision tables represent decisions and outcomes in a table format, with rows for alternatives and columns for states of nature. Decision trees show decisions and outcomes over time in a graphical format, with branches for decisions and chance events. The document also provides examples of how to construct and use decision tables and trees to analyze decision problems involving uncertainty.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
112 views79 pages

2 Modeling Tools For Decision Analysis

The document discusses two modeling tools for decision analysis: decision tables and decision trees. It provides details on the components and characteristics of each. Decision tables represent decisions and outcomes in a table format, with rows for alternatives and columns for states of nature. Decision trees show decisions and outcomes over time in a graphical format, with branches for decisions and chance events. The document also provides examples of how to construct and use decision tables and trees to analyze decision problems involving uncertainty.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 79

2 Modeling Tools for Decision

Analysis
2.1 Decision Table (payoff table)
2.2 Decision Tree
2.3 Influence Diagrams

Outcomes
States of Nature

Alternatives
Decision Problem
1
Elements of a Decision
How do we structure the problem?
(1) Objectives and means
(2) Alternatives to choose between
(3) Uncertainty in Events and Outcomes
(4) Consequences of the Decision

Outcomes
States of Nature
Alternatives
Decision Problem
2.1 Decision Table
(or pay-off table)
It is possible to represent the type of problem
we have been examining in a table called
decision matrix or pay-off table.

The decision table shows the financial


consequences (or pay-off) in terms of the
alternative decisions that can be made and the
alternative states of nature that might result.
1) The Elements of a decision
table (1/4)
In a decision table
The rows correspond to the possible decision alternatives.
The columns correspond to the possible future events.
Events (states of nature) are mutually exclusive and
collectively exhaustive.
The table entries are the payoffs.
States of Nature
Alternatives State 1 State 2
Alternative 1 Outcome 1 Outcome 2
Alternative 2 Outcome 3 Outcome 4
1) The Elements of a decision
table (2/4)
Decision table analysis can be applied when:
There is a finite set of discrete decision alternatives.
The outcome of a decision is a function of a single
future event.
Transposed decision table

Alternatives
States of Nature Alternative 1 Alternative 2
State 1 Outcome 1 Outcome 3
State 2 Outcome 2 Outcome 4
(3/4)

States of Nature
Alternatives State 1 State 2
Alternative 1 Outcome 1 Outcome 2
Alternative 2 Outcome 3 Outcome 4
transposed
Alternatives
States of Nature Alternative 1 Alternative 2
State 1 Outcome 1 Outcome 3
State 2 Outcome 2 Outcome 4
1) The Elements of a decision
table (4/4)
2) Example 1: TOM BROWN
INVESTMENT DECISION (1/5)
Tom Brown has inherited $1000.
He has to decide how to invest the money for one
year. The return on each investment depends on
the (uncertain) market behavior during the year.
A broker has suggested five potential investments.
Gold
Junk Bond
Growth Stock
Certificate of Deposit
Stock Option Hedge
2) Example1 : TOM BROWN
Solution (2/5)
Construct a payoff table.
Select a decision making criterion, and
apply it to the payoff table.
Identify the optimal decision.
Evaluate the solution.
S1 S2 S3 S4 Criterion
D1 p11 p12 p13 p14 P1
D2 p21 p22 p23 P24 P2
D3 p31 p32 p33 p34 P3
2) Example 1: The Payoff Table
(3/5)
DJA is up more DJA is up DJA moves DJA is down DJA is down more
than1000 points [+300,+1000] within [-300, -800] than 800 points
[-300,+300]

Decision Define the states


States of nature.
of Nature
Alternatives Large Rise Small Rise No Change Small Fall Large Fall
Gold -100 100 200 300 0
Bond 250 The states
200 of nature150
are mutually
-100 -150
Stock 500 exclusive
250and collectively
100 exhaustive.
-200 -600
C/D account 60 60 60 60 60
Stock option 200 150 150 -200 -150
2) Example 1: The Payoff Table
(4/5)

Decision States of Nature


Alternatives Large Rise Small Rise No Change Small Fall Large Fall
Gold -100 100 200 300 0
Determine the
Bond 250 200 150 -100 -150
set of possible
Stock 500decision250 100 -200 -600
C/D account 60alternatives.
60 60 60 60
Stock option 200 150 150 -200 -150
2) Example 1: The Payoff Table
(5/5)

Decision States of Nature


Alternatives Large Rise Small Rise No Change Small Fall Large Fall
Gold -100 100 200 300 0
Bond 250 200 150 -100 -150
Stock 500 250 100 -200 -600
C/D account 60 60 60 60 60
Stock option 200 150 150 -200 -150

The stock option alternative is dominated by the


bond alternative
3) Example 2: Keyboard
Manufacture (1/4)
A small company specializes in assembling and selling PC
systems for use by family doctor practices throughout the U.S.A.
The company is developing a new PC-based system. At present
the company is trying to decide on the manufacturing and
assembly process to be used. One aspect of this relates to the
keyboard that will be used in the system, which will have
specially labeled function keys.
The company has decided that it faces three alternatives:
It can manufacture/assemble the keyboard itself.
It can buy the keyboards from a domestic manufacturer.
It can buy the keyboards from a manufacturer in the Far East.
To help simplify the situation, the company is planning for three
possible sales levels in the future:
Low
Medium
High
3) Decision table I: without
probability (2/4)

Table 1 Decision table: profit contribution ($000s)

Future sales level


Decision Low Medium High

Manufacture (M) -15 10 55

Buy domestic (BD) 10 25 30

Buy abroad (BA) 5 20 40


Decision table II: without
probability (transposed) (3/4)
Table 2 Transposed Decision table: profit contribution ($000s)

Decision

Future sales Manufacture Buy domestic Buy abroad


level (M) (BD) (BA)
Low -15 10 5
Medium 10 25 20
High 55 30 40
Decision table III: with
probability and pay-off (4/4)

Table 3 Decision table: probability and pay-off ($000s)

Decision

Future sales Probability Manufacture Buy domestic Buy abroad


level (M) (BD) (BA)

Low 0.2 -15 10 5


Medium 0.5 10 25 20
High 0.3 55 30 40
4) In-class Example (1/2)
A manufacturing company, faced with a possible increase
in demand for its product, considers the following:

Alternatives:
1. status quo: no change
2. extend: extending their production line buying a new machine
3. build: building a new production hall with new equipment
4. cooperate: finding additional business parters for production
Uncertainty involved:
Market reaction: after the decision, the sales can increase or
decrease.
Consequences:
Expected profit, shown in decision table on the next slide
In-class Example (2/2)
2.2 Decision tree
It is frequently useful to represent the type of problem we
have been examining in graphical form by constructing
what is known as a decision tree.
The tree diagram shows the logical progression that
occurs over time in terms of decisions and
outcomes and is particularly useful in sequential decision
problems - where a series of decisions need to be made
with each, in part, depending on earlier decisions and
outcomes.
Decision tree represents the decision problem in terms of chains of
consecutive decisions and chance events.
Time proceeds from left to right.
Uncertainties associated with chance events are modeled by
probabilities.
1) Components of Decision Tree
(1/2)
1) Characteristics of a decision
tree (2/2)
State 1
Outcome 1
1
State 2
Outcome 2

State 1
Outcome 3
2
State 2
Outcome 4
Decision Node

State of Nature Node


2) Example 1 (1/5)
2) Solving Decision Trees (2/5)
2) Example 1: Solved
Decision Trees (3/5)
2) Decision Tree Development
(4/5)
1. Place decision and chance nodes in a logical
time order
2. Independent chance nodes can be placed in
any order
3. Estimate probabilities of all chance events
4. The sum of probabilities in a chance node
must be 1
5. In terminal nodes, specify consequences by a
single performance measure, e.g.:
money,
aggregate utility or
results of a multiple criteria analysis
2) Common Mistakes (5/5)
1. Decision and chance nodes are in wrong
order: Only chance nodes whose results are
known at the time of decision can precede a
decision node
2. Incorrect derivation of chance probabilities:
Chance probabilities depend on each other
and decisions made
3. Chance events with probability 0 can be
left out
4. When solving the tree: Maximizing instead
of minimizing, or vice versa
3) Example 2: (1/4)
Low The decision tree starts from the left-
hand side and gradually moves across
M Medium to the right.
A box is used to indicate that at this
High point we must take a decision (the box
Low is technically known as a decision node)
The three alternatives branch out
BD Medium from this node:
Mg to manufacture (M)
High to buy domestically (BD)
to buy abroad (BA)
Low Each of these branches leads to a
BA Medium outcome node (indicated by a circle),
which presents the possible states of
High nature:
Low (L)
Fig. 1 Decision tree I Medium (M)
High (H)
3) Decision tree with pay-off
(2/4)
Low With the pay-off information,
-15
M which of the three alternative
Medium decisions would you recommend?
10
High The answer has to be: it
55 depends.
Low 10 How reliable you think the
BD Medium information is?
Mg 25
How risky the various
High 30 options are?
Low How critical the decision is
5 to the companys future?
BA Medium
20
High The key factor will depend on
40 your own attitude to these
Fig. 2 Decision tree with pay-off future sates of nature.
(value in $000s)
3) Completed decision tree
(3/4)
Low 0.2 Let us assume that the company
-15 has been able to quantify the
M Medium 0.5 likelihood of each of the states of
10 nature occurring by attaching a
High 0.3
55 probability to each.
Low 0.2 10 Such probabilities may have

BD been derived from market


Medium 0.5 research, from sales forecasting,
Mg 25
High 0.3 or may simple be guesstimate
30 based on some hard evidence and
Low 0.2 the experience of the decision
5
maker.
BA Medium 0.5
20 The probability of low sale is
High 0.3 assessed at 0.2, medium at 0.5
40 and high at 0.3. Note that, they
Fig. 3 Completed decision tree must sum to 1 to include all
(pay-off and probability) possible outcomes.
3) Solved decision tree
(4/4)
EMV(M)=18.5 Low 0.2
-15
M Medium 0.5 The EMV for the decision of M is:
10
High 0.3 -150.2+ 100.5+ 550.3=18.5
EMV(BD)=23.5 55
Low 0.2 10
BD Medium 0.5 The EMV for the decision of BD is:
Mg 25 100.2+ 250.5+ 300.3=23.5
High 0.3
30
EMV(BA)=23 Low 0.2
5
BA Medium 0.5 The EMV for the decision of BA is:
20 50.2+ 200.5+ 400.3=23
High 0.3
40
Fig. 4 Solved decision tree
4) Key Characteristics of a
Decision Tree (1/4)
(1) Time in a decision tree flows from left to right, the
placement of the decision nodes and the event nodes is
logically consistent with the way events will play out in
reality. Any event or decision that must logically precede
certain other event and decisions is appropriately placed
in the tree to reflect this logical dependence.
(2) The branches emanating from each decision node
represent all of the possible decisions under consideration
at that point in time under the appropriate circumstances.
4) Key Characteristics of a
Decision Tree (2/4)
(3) The branches emanating from each event node
represent a set of mutually exclusive and collectively
exhaustive outcomes of the event node.
(4) The sum of the probabilities of each outcome ranch
emanating from a given event node must sum to one.
(5) Each and every final branch of the decision tree
has a numerical value associated with it. This numerical
value usually represents some measure of monetary
value, such as salary, revenue, cost, etc.
4) In-Class Example (3/4)
Mobon Oil Company has a lease on an offshore oil site.
The lease is about to expire and they are faced with
either developing the field or selling the lease to Excel
Oil Co. for $50,000. It costs approximately $100,000 to
drill a well.
There is a 45% chance that the well is dry, a 45%
chance that the well will have a minor strike and a
10% chance that they will have a major strike.
For a typical minor strike the revenues average
$300,000. If the strike is major the revenues average
$700,000.
What should Mobon do?
4) In-Class Example (4/4)
5) Sequential Decision Making:
An Example (1/6)
An engineer who works for a company which produces
equipment for the food processing industry has been asked
to consider the development of a new type of processor and
to make a recommendation to the companys board.
Two alternative power sources could be used for the
processor, namely gas and electricity, but for technical
reasons each power source would require a fundamentally
different design. Resource constraints mean that the
company will only be able to pursue one of the designs, and
because the processor would be more advanced than others
which have been developed it is by no means certain that
either design would be a success.
The engineer estimates that there is a 75% chance that the
electricity-powered design would be successful and only a
60% chance that the gas-powered design would be a
success.
5) An initial decision tree for the
food-processor problem (2/6)
5) Second Decision Making
(3/6)
After considering this tree the engineer realizes
that if either design failed then the
company would still consider modifying the
design, though this would involve more
investment and would still not guarantee success.
He estimates that the probability that the
electrical design could be successfully modified is
only 30%, though the gas design would have an
80% chance of being modified successfully.
5) Sequential decision tree for
the food-processor problem (4/6)
5) Rollback Method for Sequential
Decision Making (5/6)
The technique for determining the optimal
policy in a decision tree is known as the
rollback method.
To apply this method, we analyze the tree
from right to left by considering the later
decisions first.
The rollback method allows a complex
decision problem to be analyzed as a series of
smaller decision problems.
(6/6)
6) In-class Example 2
(1/8)
Jenny Lind is a writer of romance novels. A
movie company and a TV network both want
exclusive rights to one of her more popular
works. If she signs with the network, she will
receive a single lump sum, but if she signs
with the movie company, the amount she will
receive depends on the market response to
her movie. What should she do?
Payouts and Probabilities
(2/8)
Movie company Payouts
Small box office - $200,000
Medium box office - $1,000,000
Large box office - $3,000,000
TV Network Payout
Flat rate - $900,000
Probabilities
P(Small Box Office) = 0.3
P(Medium Box Office) = 0.6
P(Large Box Office) = 0.1
Jenny Lind - Payoff Table
(3/8)

States of Nature
Small Box Medium Box Large Box
Decisions Office Office Office
Sign with Movie
$200,000 $1,000,000 $3,000,000
Company
Sign with TV
$900,000 $900,000 $900,000
Network
Prior
0.3 0.6 0.1
Probabilities
Using Expected Return Criteria
(4/8)

EVmovie=0.3(200,000)+0.6(1,000,000)+0.1(3,000,000)
= $960,000
EVtv =0.3(900,000)+0.6(900,000)+0.1(900,000)
= $900,000
Therefore, using this criteria, Jenny should select the
movie contract.
Solved Payoff Table
(5/8)

States of Nature
Decisions
Small Box Medium Large Box
EMV
Office Box Office Office
Sign with Movie
$200,000 $1,000,000 $3,000,000 $960,000
Company
Sign with TV
Network
$900,000 $900,000 $900,000 $900,000
Prior
0.3 0.6 0.1
Probabilities
Jenny Lind - Decision Tree
(6/8)
Small Box Office
$200,000

Sign with Movie Co. Medium Box Office


$1,000,000

Large Box Office


$3,000,000

Small Box Office


$900,000

Sign with TV Network Medium Box Office


$900,000

Large Box Office


$900,000
Jenny Lind - Decision Tree
(7/8)
Small Box Office
ER $200,000
.3
?
Sign with Movie Co. Medium Box Office
.6 $1,000,000
ER .1
? Large Box Office
$3,000,000

Small Box Office


ER $900,000
.3
?
Sign with TV Network .6 Medium Box Office
$900,000
.1
Large Box Office
$900,000
Jenny Lind Solved Decision Tree
(8/8)
Small Box Office
ER $200,000
.3
960,000
Sign with Movie Co. .6 Medium Box Office
$1,000,000
ER .1
960,000 Large Box Office
$3,000,000

Small Box Office


ER .3 $900,000
900,000
Sign with TV Network .6 Medium Box Office
$900,000
.1
Large Box Office
$900,000
2.3 Influence Diagram
An influence diagram (ID) (also called a relevance
diagram, decision diagram or a decision network)
is a compact graphical and mathematical representation
of a decision situation.
ID was first developed in the mid-1970s by decision
analysts with an intuitive semantic that is easy to
understand.
1) Motivation for Influence
Diagrams (1/7)
When a decision tree have too many decision
alternatives and chance variables, it turns
into a very complex structure. Influence
diagram is now adopted widely and becoming an
alternative to the decision tree.
1) Motivation for Influence
Diagrams: an Example (2/7)
1) Motivation for Influence
Diagrams: an Example (3/7)
1) Motivation for Influence
Diagrams: an Example (4/7)
1) Influence Diagram vs.
Decision Tree (5/7)
Influence Diagram Decision Trees
1. Gives basic 1.Gives detailed
information information

2. Less messy 2.More messy due to


greater details

3. Graphically more 3.Not so appealing


appealing when
presented to upper
management
1) Influence Diagram vs.
Decision Tree (6/7)
DT display more information, the details of a problem,
but they may become messy.
ID show a general structure of a problem and hide
details.
ID are particularly valuable for the structuring phase
of problem solving and for representing large
problems.
Solving algorithms: DT straightforward, ID difficult
Any properly built ID can be converted into a DT, and
vice versa.
1) Motivation for Influence
Diagrams (7/7)
Influence diagram is a:
high-level (compact),
visual representation
displaying relationships between essential
elements that affect the decision.

Two levels of detail:


higher: only elements and relations
lower: detailed information defined with each
element
2) Elements of Influence
Diagrams (1/5)
The Influence Diagram
presents decision problem in
the form of a non-circular,
directed graphic derived
from nodes and directed
arcs that interconnect with
these nodes.

Fig.2.3.1 A Simple Influence Diagram


2) Elements of Influence
Diagrams (2/5)
2) Arcs in Influence Diagrams
(3/5)
Decision A affects the probabilities of
event B;
Decision A is relevant for event B

The outcome of event A affects the


probabilities of event B;
Event A is relevant for event B

Decison A occurs before decision B;


Decisions A and B are sequential

Decision B occurs after event A;


The outcome of A is known when
deciding about B
2.3.2 Rules for Influence Diagram
(4/5)
RULE 1: There can be no cycles.
That is, it must always be impossible to return to
any element in the diagram by following arrows in
the direction that they point.
A loop would show that a node (variable) both
influences and is influenced by another node.
Such a relationship could not be represented by
the left-to-right ordering of influences represented
by a decision tree.
2.3.2 Rules for Influence Diagram
(5/5)
RULE 2: ONE VALUE MEASURE.
All decisions represented in the diagram must be made
to optimize the same value measure. However, multiple
value nodes can be used to calculate one value measure.

RULE 3: NO FORGETTING.
Any information known when a decision is made must
be remembered perfectly when any subsequent decision
is made. This implies that between every pair of
decisions in an influence diagram, there must be a
directed path that includes only decision nodes. And, if
there is an arrow from an uncertainty to a decision,
there must also be an arrow from that uncertainty to
any subsequent decision.
3) Developing Influence
Diagrams: an Example (1/4)
The Quality Wilton Ltd. produces carpets. A special type of carpet they
produce is sold for a price of 32 per square meter in the U.K. The
product of the company is considered to fall into the category of luxury
commerce item in the United Arab Emirates (U.A.E.) and sold for a price
of 56.
Since the product is accepted to be a luxury item, the prices are
influenced by the state of economy in export country. The company
management is expecting a recession (decline) in the U.A.E. economy. It
is stated by company authorities that the next 12 months are important
for the orders placed. There is an economical recession (decline)
anticipation based on local inflation and low commercial values. The
company will export its product immediately or it will wait for
another 6 or 12 month to do it.
The executives of the carpet company foresee three different scenarios for
the U.A.E. These are stable economical conditions, slightly worse
condition and severely bad conditions. The pay-off matrix for the
problem and probabilities assigned by the company authorities for
economical state are given in Table 2.
3) Developing Influence
Diagrams: an Example (2/4)
Table 2. Pay-off matrix for Quality Wilton Ltd. ()
(3/4)
Influence Diagram
for Quality Wilton Ltd. (4/4)
4) Gradual Development of
Influence Diagrams
Two basic strategies:
Start with outcomes and model towards
decisions and events;
Gradually add more and more detail.
4) Example 1: Gradual
Development (1/3)
4) Example 1: Gradual
Development (2/3)
4) Example 1: Gradual
Development (3/3)
5) Example 2: Multiple Objectives
(1/1)
Two
Objectives

Single
Objective
6) Example 3: Intermediate
Calculations (1/1)
7) In-class Exercise 3: Tractor
Buying (1/2)
Your uncle is going to buy a tractor. He has two
alternatives:
1. A new tractor (17 000 )
2. An used tractor (14 000 )
The engine of the old tractor may be defect, which is
hard to ascertain. Your uncle estimates a 15 %
probability for the defect.
If the engine is defect, he has to buy a new tractor
and gets 2000 for the old one.
Before buying, your uncle can take the old tractor to
a garage for an evaluation, which costs 1 500 .
If the engine is OK, the garage can confirm it without
exception.
If the engine is defect, there is a 20 % chance that the
garage does not notice it.
7) In-class Exercise 3: Tractor
Buying (2/2)

1. Solve the decision tree


2. Develop equivalent influence diagram
8) Turning an influence diagram
into a decision tree (1/3)
One step-by-step procedure for turning an influence
diagram into a decision tree is as follows:
(1) Identify a node with no arrows pointing into it (since there can
be no loops at least one node will be such).
(2) If there is a choice between a decision node and an event node,
choose the decision node.
(3) Place the node at the beginning of the tree and remove the
node from the influence diagram.
(4) For the now-reduced diagram, choose another node with no
arrows pointing into it. If there is a choice a decision node should be
chosen.
(5) Place this node next in the tree and remove it from the
influence diagram.
(6) Repeat the above procedure until all the nodes have been
removed from the influence diagram.
8) An Example: (2/3)
(3/3)
Homework 1:
An investor is having three options of buying a
real estate:
an apartment building
an office building
a warehouse.
There are two future states of nature considered:
(a) good economic conditions
(b) poor economic conditions
The pay-offs (i.e., profits) that will result from
each decision in the event of each state of nature
and the probabilities of occurrence of the states
of nature are given in the pay-off table as below :
Homework 1: (cont.)
Q1: Draw the decision tree.
Q2: Which one the investor should buy?
Q3: Do the sensitivity analysis to probability of good
economic conditions.

States of Nature
Good Economic Conditions Poor Economic Conditions
Decisions (Probability=0.6) (Probability=0.4)
Apartment
$100,000 $60,000
building
Office
$200,000 $-80,000
building
Warehouse $60,00 $20,000
The end

You might also like