Decision Theory

EXAMPLE
ABC Company is planning to manufacture its own new PC based

system, which intends to be marketed by next year under its own
brand. One particular concern of the company has something to do
with the keyboard that will be used in the system, which will be
having a special feature on function keys.
The following are the different decision alternatives identified
by the management:
a. The company can manufacture its own unique keyboard
b. The company can buy the keyboards from a local manufacturer.
c. The company can buy the keyboards from Japan.
Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

continuation…
The payoff table is given below. The profit contribution is in

thousand pesos
Future Sales Level

Alternatives Low Moderate High
Manufacturer -30 20 110
Buy from local 20 60 50
Buy from Japan 10 45 80

Decision Theory
Jonecis A. Dayap
University of San Jose-Recoletos

OUTLINE
Introduction
Decision - Making
Decision Environments
Expected Value of Perfect Information
Decision Tree Analysis

Learning Objectives
Define decision and apply the steps in decision–

making.
Identify the different decision environments.
Solve decision-making under certainty, uncertainty and
risk.

INTRODUCTION
In business, managers always make decision to ensure

the efficient and effective operation of the business.
Examples of business problems that demand decision :
1. What marketing strategy to utilize?

2. How many sales representatives to hire?
3. What selling price to impose on the product?
Remark: Decision makers should make careful evaluation of the different

alternatives and select the best alternative that would meet the requirement on
solving the problem based on the criteria and in accordance with the
organization’s objective .
Decision - Making
 It is an act of selecting a preferred course of action among
alternatives.
Monitor Identify
Implement Determine
Select Search
Evaluate
Decision Environments
1. Decision Making Under the Condition of Certainty

Decision maker knows which state of nature will occur.
2. Decision Making Under the Condition of Uncertainty

Decision maker estimates of the probability of the events.
3. Decision Making Under the Condition of Risk

Decision maker computes the chance of each event based on the
existing information

1. Maximax Strategy
 The decision maker has to choose the alternative with the
maximum among the maximum payoffs.
 It is also known as the optimistic approach.
Risk – seeker management
Remark: In case the problem is cost minimization, to apply the

preceding strategy, one has to choose the minimum payoff for each
alternative, then finally select the minimum. Thus, this is called
“minimin” for cost.

2. Maximin Strategy
 The decision maker has to choose the alternative with the
maximum among the minimum payoffs.
 It is also known as the pessimistic approach.
Risk averter management
Remark: In case the problem is minimization of cost, to apply the

preceding strategy, one has to select the miximum payoff for each
alternative, then finally choose the minimum. Thus, this is called
“minimax” for cost.

3. Laplace Strategy
 Used to select the alternative with the maximum average payoff.

To compute the value, simply determine the average payoff
for each alternative and then choose the alternative with the
maximum average payoff (profit).
Remark: For cost problem, simply do the same then finally, choose
the alternative with the minimum average payoff.

4. Hurwicz Criterion of Realism
 This strategy is a middle ground criterion between the maximax

and maximin.
The decision maker can assign a value for coefficient or index of
optimism symbolized by the Greek letter α (alpha) with a
value between 0 and 1.
Measure of Realism = α (best payoff) + (1 – α )(worst payoff)
Remark: Choose the maximum value of MR for profit (max MR) and
minimum value of MR for cost (min MR).

5. Minimax Regret Strategy
The decision maker choose the alternative that would minimize

the maximum regret.
To apply this strategy, first determine the regret payoff for each
alternative under each state of nature, then determine the
maximum regret or loss payoff for each alternative, and
finally selecting the minimum among the maximum regrets.
For Profit : Regret value = Highest column entry – every column
entry.
For Cost : Regret value = Every column entry – lowest column
entry.
3. Decision Making Under the Condition of Risk
The decision maker does not know exactly which one among the
different states of nature will occur but can estimate that
any one state will occur.
 To apply this strategy the mathematical expectation(ME) or
expected value (EV) has to be computed by getting the product of
the ( P ) probability of an event and the ( X )amount to be received
upon the occurrence of that event.
 EV = P1(X1) + P2(X2) +…+ Pn(Xn)
The decision maker choose the alternative that has the highest
expected value.
EXAMPLE
ABC Company is planning to manufacture its own new PC based
system, which intends to be marketed by next year under its own
brand. One particular concern of the company has something to do
with the keyboard that will be used in the system, which will be
having a special feature on function keys.
The following are the different decision alternatives identified
by the management:
a. The company can manufacture its own unique keyboard
b. The company can buy the keyboards from a local manufacturer.
c. The company can buy the keyboards from Japan.

continuation…
The payoff table is given below. The profit contribution is in

thousand pesos
Future Sales Level


1. Decision making under the condition of certainty
 If the management is certain that the condition of
economy is LOW, the best decision is to buy from local

manufacturer.
 If the condition of economy is MODERATE, the best
decision is to buy from local manufacturer.

 If the condition of the economy is HIGH, the best
decision is to manufacture.

2. Decision making under the condition of uncertainty
a. Applying the Maximax Strategy

Future Sales Level
Decision : Since the maximum among the three maximum values refers to
the alternative of manufacture, therefore ABC Company will manufacture
its own unique keyboard

b. Applying the Maximin Strategy

Future Sales Level
Decision : Since the maximum among the minimum payoffs refers to the
decision on buying from local suppliers, therefore ABC Company will buy
the keyboards from local suppliers.

c. Applying Laplace Strategy

Alternatives Future Sales Level
Low Moderate High
Alternatives Row Total Row Average

Manufacture 100 33.33
Buy from local 130 43.33
Buy from Japan 135 45.00
Decision : The maximum average refers to the third alternative, which is to
buy the units from Japan.

d. Applying Hurwicz Strategy with α = 60% as a coefficient of

realism:
Low Moderate High
Manufacture = (0.60)(110) + (0.40)(-30) = 54

Buy from local = (0.60)(60) + (0.40)(20) = 44
Buy from Japan = (0.60)(80) + (0.40)(10) = 52
Decision :The best alternative is to manufacture

e. Applying the Minimax Regret Strategy

Low Moderate High
Alternatives Future Sales Level Maximum Regret
Low Moderate High Regret
Manufacturer 50 40 0 50 Table
Buy from local 0 0 60 60
Buy from Japan 10 15 30 30
Decision : The minimum regret payoff refers to the third alternative,
which is to buy the units from Japan.

3. Decision making under the condition of risk

Low Moderate High
State of Low Moderate High

Nature EV = P(X)
Probability 25% 60% 15%
Manufacture = (0.25)(-30) + (0.60)(20) + (0.15)(110) = 21.0

Buy from local = (0.25)(20) + (0.60)(60) + (0.15)(50) = 48.5
Buy from Japan = (0.25)(10) + (0.60)(45) + (0.15)(80) = 41.5
Decision : The best alternative is to buy from local supplier because it has
the highest expected value
Problem Set 1.1
1. President Steven Ji of MAC Motors is considering whether or not to
build a manufacturing plant in Cavite City. Upon analyzing the
different associated costs and factors to be considered in his plan, he
was able to make a profit-payoff table as summarized below:
STATES OF ECONOMY
Alternatives Expand Contract Unchanged
(20%) (45%) (35%)
No new plant 200 -30 40
Build small plant 300 -60 60
Build large plant 400 -120 80
Values are in million pesos.
Determine the best alternative using the different strategies below:
a. Maximax f. Expected Value Criterion
b. Maximin
c. Laplace
d. Hurwicz ( α = 0.40)
e. Minimax Regret
Assignment 1.1
Cost Payoff Matrix
Investment Possible Inflation Rates Next Year
Alternatives 5% 10% 15%
Stocks 120,000 100,000 90,000
Gold 70,000 100,000 140,000
Business 80,000 90,000 100,000
Probability 0.2 0.5 0.3
Determine the best alternative using the different strategies below:

a. Minimin f. Expected Value Criterion
b. Minimax
c. Laplace
d. Hurwicz ( α = 0.40)
e. Minimax Regret

Assignment 1.2
Zed and Adrian run a small bicycle shop called "Z to A Bicycles". They
must order bicycles for the coming season. Orders for the bicycles must
be placed in quantities of twenty (20). The cost per bicycle is $70 if they
order 20, $67 if they order 40, $65 if they order 60 and $64 if they order
80. The bicycles will be sold for $100 each. Any bicycles left over at the
end of the season can be sold (for certain) at $45 each. If Zed and Adrian
run out of bicycles during the season, then they will suffer a loss of
"goodwill" among their customers. They estimate this goodwill loss to be
$5 per customer who was unable to buy a bicycle. Zed and Adrian
estimate that the demand for bicycles this season will be 10, 30, 50, or 70
bicycles with probabilities of 0.2, 0.4, 0.3, and 0.1 respectively.
a) Construct a payoff table for this problem.
b) What course of action would you recommend using each of
the following strategies ( Maximax, Maximin, Laplace ,
Minimax Regret and Expected Value Method ) ?
Activity 1
Finicky's Jewelers sells watches for $50 each. During the next month, they
estimate that they will sell 15, 25, 35, or 45 watches with respective
probabilities of 0.35, 0.25, 0.20, and ... (figure it out). They can only buy
watches in lots of ten from their dealer. 10, 20, 30, 40, and 50 watches cost
$40, 39, 37, 36, and 34 per watch respectively. Every month, Finicky's has
a clearance sale and will get rid of any unsold watches for $24 (watches
are only in style for a month and so they have to buy the latest model each
month). Any customer that comes in during the month to buy a watch, but
is unable to, costs Finicky's $6 in lost goodwill.
a) Construct a payoff table for this problem.
b) What course of action would you recommend using each of
the following strategies (Maximax, Maximin, Laplace,
Minimax Regret and Expected Value Method ) ?
OUTLINE
Expected Value of Perfect Information
Decision Tree Analysis

Expected Value of Perfect Information ( EVPI )
 If the managers are able to determine which among the states of
nature will occur, definitely, they know which decision will be
the best for the company
 Expected Value of Perfect Information ( EVPI ) is the price that
one would be willing to pay in order to gain access to perfect
information .
Perfect information – All consumers and producers know all prices
of products and utilities each person would get from owning
each product.
The payoff increases as we determine the certainty of a particular
expected value of perfect information.

Method 1
Take the difference between the expected payoff under certainty and
the expected payoff under condition of risk.
Steps :
1. Multiply the best payoff under each state of nature to its
probability.
2. Get the sum of these combined weights.
3. Subtract the highest payoff of the result in decision-making
under the condition of risk from the sum of the
combined weights.
4. The difference is the value of perfect information.
EVPI = Expected Value under Certainty – Maximum EV under Risk

Method 1

State of Nature Low Moderate High

EV under certainty = ( 20 x 0.25 ) + ( 60 x 0.60 ) + ( 110 x 0.15 )
= 57.5
MEV under risk = 48. 5
EVPI = EV under certainty - MEV under risk
= 57.5 – 48.5
= 9.0
Method 2
Find the expected regret value for each alternative then EVPI is the
smallest expected value..
Steps :
1. Construct Regret Table.
2. Multiply each entry by the probability value of each state of
nature of every alternative
3. Get the sum of these combined weights.
3. The lowest expected value is EVPI

Method 2

Regret Table
Alternatives Low Moderate High Maximum
Regret
Manufacturer 50 40 0 50
Method 2
Regret Table
Alternatives Low Moderate High Maximum
Regret
Manufacturer 50 40 0 50
Solution :
1. Manufacture 50(0.25) + 40(0.60) + 0(0.15) = 36.5
2. Buy from local 0(0.25) + 0(0.60) + 60(0.15) = 9.0
3. Buy from Japan 10(0.25) + 15(0.60) + 30(.15) = 16.0
Example
The management of the RDM Company must decide if they are going to
give their workers a wage increase or not. The company will reduce its
annual profits once they have decided to give an increase to their workers
and it will avoid a possible strike. However, if the management choose not
to give the increase to their annual profits. The possible annual profit is
determined by the economy. If the company will experience a favorable
economy, it will give them a good profit ; if the company will experience
an unfavorable economy, it will make little or no profit at all. The
expected payoff in millions of pesos is given below.
Alternatives Favorable Unfavorable
Give the wage increase 200 0
Do not give the wage increase 300 100
If favorable economy has a probability of 65%, determine the ff:

1. EV of each alternative
2. EVPI
Decision Tree Analysis

Example
Owel is planning to open up a new branch of Engrande Lechon at a new
location in Pasig or expand the existing branch located in Marikina City.
Demand on the new location is expected to be 60% high and 40% low. Fixed
cost will reach the amount of Php 150,000. If the demand becomes high , he
expects to have a revenue of Php 250,000, however if the demand becomes low,
he could only expect a revenue of Php 200,000. Upon analyzing the situation in
his existing branch, he believes that by introducing new recipes the sales will
reach the amount of Php 120,000 if the demand becomes high. However, if the
demand becomes low, he could only expect Php 80,000 revenue. Projection on
high demand in the existing branch tends to be 55% and upon computing the
fixed cost it would reach the amount of Php 50,000. If you were the consultant
of Owel, what would you advise?
Solution
Information Table for Owel’s Decision Situation

States of Nature
Alternatives Expenses
Probability
Revenue
High Low High Low
Open a new
branch 60% 40% Php 250,000 Php 200,000 Php 150,000
Expand the
existing 55% 45% Php 120,000 Php 80,000 Php 50,000
branch
continuation…
Solution
Decision Tree Diagram
P(High)= 60% R = 250,000
E = 150,000
100,000
80,000
P( Low ) = 40%
R = 200,000
Open E = 150,000
50,000
/
Expand
P(High)= 55% R = 120,000
E = 50,000
70,000
52,000
P(Low)= 45% R = 80,000

E = 50,000
30,000
Example
Consider a situation in which the management of RST
Company must decide in choosing an ideal location to open a
new branch of computer shop. The table below shows the
different costs to operate the business in different locations and
the probabilities on sales events.
Locations Low Moderate High
Cubao Php 75,000 Php 85,000 Php150,000
Gilmore Php 100,000 Php 120,000 Php 150,000
Makati Php 150,000 Php170,000 Php200,000
Probability 0.30 0.50 0.20

Problem Set 1.2
1. A physician is involved in Ph2 million malpractice suit. He can

either settle out of court for Php500,000 or go to the court. If he
goes to the court and loses, he must pay the amount of
Php1,750,000 with the additional of Php250,000 for court costs. If
he wins in the court, the plaintiff will be the one to pay the court
costs.
a. Construct a payoff table for this problem.
b. Consider the physician’s lawyer estimates that the probability of
winning is 0.30. Draw a decision tree and determine the best
solution.

References:
Arao, Rosalia R., et.al.(2009). Quantitative Approaches in Decision-making with
Computer Application. Rex Book Store.
Anderson, D. R., Sweeney, D. J., Williams, T. A., Camm, J. D., & Cochran, J. J.
(2018). An Introduction to Management Science: Quantitative Approach.
Cengage learning.


Decision Theory

Caricato da

Informazioni sul documento

Titolo originale

Copyright

Formati disponibili

Condividi questo documento

Condividi o incorpora il documento

Opzioni di condivisione

Hai trovato utile questo documento?

Questo contenuto è inappropriato?

Copyright:

Formati disponibili

Decision Theory

Caricato da

Copyright:

Formati disponibili

EXAMPLE

ABC Company is planning to manufacture its own new PC based

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

The payoff table is given below. The profit contribution is in

Future Sales Level

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

Expected Value of Perfect Information

Decision Tree Analysis

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

Define decision and apply the steps in decision–

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

In business, managers always make decision to ensure

Examples of business problems that demand decision :

1. What marketing strategy to utilize?

Remark: Decision makers should make careful evaluation of the different

1. Decision Making Under the Condition of Certainty

2. Decision Making Under the Condition of Uncertainty

3. Decision Making Under the Condition of Risk

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

Remark: In case the problem is cost minimization, to apply the

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

Remark: In case the problem is minimization of cost, to apply the

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

 Used to select the alternative with the maximum average payoff.

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

 This strategy is a middle ground criterion between the maximax

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

The decision maker choose the alternative that would minimize

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

The payoff table is given below. The profit contribution is in

Future Sales Level

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

 If the management is certain that the condition of

economy is LOW, the best decision is to buy from local

decision is to buy from local manufacturer.

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

a. Applying the Maximax Strategy

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

b. Applying the Maximin Strategy

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

c. Applying Laplace Strategy

Alternatives Row Total Row Average

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

d. Applying Hurwicz Strategy with α = 60% as a coefficient of

Manufacture = (0.60)(110) + (0.40)(-30) = 54

Decision :The best alternative is to manufacture

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

e. Applying the Minimax Regret Strategy

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

Alternatives Future Sales Level

State of Low Moderate High

Manufacture = (0.25)(-30) + (0.60)(20) + (0.15)(110) = 21.0

Determine the best alternative using the different strategies below:

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

Expected Value of Perfect Information

Decision Tree Analysis

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

EVPI = Expected Value under Certainty – Maximum EV under Risk

Quantitative Analysis in Business Decision Theory Jonecis A. Dayap

Alternatives Low Moderate High

State of Nature Low Moderate High