12/06/24 1

Chapter 4: Decision Theory

4.1. Introduction to Decision Theory.
4.2.Decision-making environments:
4.2.1.Decision-making under certainty,
4.2.2.Decision-making under uncertainty
4.2.3.Decision-making under risk situations
,

12/06/24 2
 4.1. Introduction to decision
theory
A general approach to decision making that is
suitable to a wide range of operations,
management decisions

 Decision theory (or the theory of choice) is a

branch of applied probability theory and analytic
philosophy concerned with the theory of making
decisions based on assigning probabilities to
various factors and assigning numerical
consequences to the outcome.

12/06/24 3
The quantitative approach in decision-making requires that,

 problems be defined, analyzed and solved in a

conscious, rational, systematic and scientific
manner based on data, facts, information, and
logic and not on mere whims and guesses

 It is a scientific approach by which quantitative

evidences are generated through modeling up on
which sound decision can be made by the decision
maker

12/06/24 4
Decision Making:
It is the process of selecting a feasible course of
action from a set of alternative, so as to solve
problems.

The process of identifying, developing, and

evaluating alternative courses of action to select the
most feasible and optimal one, in order to solve
identified problems or achieve predetermined
objectives.
Decision making is the most vital aspect in
management, in the business environment decisions
made at the right time with adequate analysis and
deliberations ensure success
12/06/24 5
Elements or Components of Decision Making
1. The acts (Alternatives)
are the alternative courses of action of strategies that are
available to the decision maker.
A set of mutually exclusive decisions that are available to the
decision maker.
2. Event or states of nature
Are an actual events that may occur in the future
A set of possible future conditions or events beyond the control
of the decision maker
3. Payoff
An out come resulted from the interaction between
alternatives set and state of nature such as profits,
revenue, costs, loss etc

12/06/24 6
Steps in Decision Making (six steps)
1.Clearly define the problem at hand:
A company wants to maximize its profit but get difficulty of deciding whether
to expand current plant, construct new plant or subcontract production for extra
demand
2. List all the available alternatives/strategies that can be
considered in decision:
Strategies or courses of actions like; expand the current plant, construct a new
plant or subcontract production for extra demand.
For example suppose that a real estate developer plans to develop a building.
After careful analysis, the developer lists the following acceptable alternatives.
 Residential
 Hospital
School
 Hotel
Other example for an investor who wants to establish plant in a given country,
the possible list of alternatives could be
Establishing large plant
Medium size plant
Establishing small plant
Establishing no plant

12/06/24 7
3. Identify expected future events or State of Nature:
State of nature refers to a set of possible future conditions or events
beyond the control of the decision maker that will be the primary
determinants of the eventual consequence of the decision.
Suppose in the case of the real state developer, the main factor that that will
influence the profitability is the state of the economic development that will
be achieved in the future.
Examples:

 Low economic growth

 Medium economic growth
 High economic growth
Another example:

high demand,
moderate demand,
low demand and
 no demand as State of Natures for the product
produced (new product)
12/06/24 8
4. Listing Payoffs
In order for a decision maker to be able to rationally approach a decision
problem, it is necessary to have some idea of the payoffs that would be
associated with each decision alternative and the various states of nature.

The payoffs might be

profits,
revenue,
costs, or
other measure of value.
Pay off table
The payoff table is a device a decision maker can use to summarize and
organize information relevant to particular decision.

It includes a list of alternatives, the possible future state of nature and
payoffs associated with each of the alternative / state of nature combinations.

12/06/24 9
Example1:
Identify conditional values for the profits for
large plant, small plant, and no development
for the possible market condition

State of nature
Alternatives High Moderate Low
Large plant 200,000 100,000 -120,000
Small plant 90,000 50,000 -20,000
No plant 0 0 0
Solution and analysis are then used to aid in decision-
making.

12/06/24 10
Example 2.

5. Select the best alternative

Suppose that the values represent profits in million birr.
Hence if the residential is chosen and if the economic growth is low the
developer realize a profit of birr 4,000,000.
Similarly if hotel is selected and if the economic growth is low, the
developer will lose birr 1,000,000, similarly there are nine payoffs.
6. Apply or Make decision
Choose the best alternative and implement or make a decision
12/06/24 11
4.2. Decision Making Environments
The environmental circumstances under which decisions
are made dictate the degrees of certainty felt by the decision
maker.

The quality of the decisions made in an organization will

dictate the success or failure of the said business.

So all the available information and alternatives must be

studied before arriving at an important decision.

Another factor that affects these decisions is the

environment in which they are taken.

There are a few different types of environments in which

these decisions are made and the type of decision making
environment has an impact on the way the decision is taken
12/06/24 12
Types of decision making environments
 Based on the availability of information during the
decision making, there are three decision making
environment.

 These are:
1: Decision making under certainty

2: Decision making under uncertainty

3: Decision making under risk

12/06/24 13
4.2.1. Decision Making Under Certainty Environment
This assumes that all relevant information required to make decision are certain and well
known.
The decision maker is with complete knowledge, stability and no ambiguity.
To make decision, the manager will have to be quite aware of the strategies available and their
payoffs and each strategy will have unique payoff resulting in certainty.
Adequate and reliable information is available. We know the cause & effect relationships.
Example
Let’s say that you have 1,000,000 birr to invest for a 1-year period. One alternative
is to open a savings account paying 6% interest (I=60,000) and another is to invest in
a government Treasury bond paying 10% interest (I=100,000)
If both investments are secure and guaranteed, there is a certainty that the Treasury
bond will pay a higher return. The return after one year will be 100 ,000 in interest.
If the developer mentioned in the previous example knows that the economic growth is low,
he/she select hospital as the best alternatives because it results a profit of birr 5,000,000 and the
like.
Decision criteria: since complete information is available no need for special criteria
12/06/24 14
 4.2.2. Decision Making Under Uncertainty
Environment
When the decision-maker faces multiple states of nature but
has no means to arrive at probability values to the likelihood of
occurrence of these states of nature,

Example: when a new product is introduced in the market or a

new plant is set up.

In business, there are many problems of this ‘nature’.

The choice of decision largely depends on the personality of

the decision-maker.

12/06/24 15
 Decision Criteria Under Uncertainty
Environment

There are several criteria for making decisions

under uncertainty:

1.Maxi-max Criterion (Optimist)

2.Maxi-min Criterion (Pessimist)

3.Mini-max Regret Criterion (Conservative)

4.Laplace Criterion (Equally likelihood)

5.Criterion of realism
12/06/24 16
A. Maxi-max decision criterion (criterion of optimism)

Under this method the best payoff for each alternative is identified and the
alternative with the maximum of these is the designated decision (identifying
the best from the best alternatives).

because the decision maker assumes the best things will occur/decision
maker assumes that the most favorable state of nature for each
alternative will occur (optimistic decision maker).It is the optimistic view

The term ‘ maxi-max’ is an abbreviation of the phrase maximum of

maximums, the optimistic approach/ best of the best

12/06/24 17
Example 1:
An investor is to invest on one of three types of real estate. The
investor must decide among an apartment building, an office
building, and a warehouse.

The future states of nature that will determine how much profit
the investor will make are good economic conditions and poor
economic conditions.
Sate of nature
Alternatives Good Poor
Economic Economic
Condition Condition
Apartment 50000 30000
building
Office building 100000 -40000
12/06/24 18
 Locate the maximum payoff for each
alternative.
 Select the alternative with the maximum
number
 Q. What would be optimum decision according to Maxi-max
Alternatives Good Poor Maximu Maximu
criteria? Economic Economic m of m of All
Condition Condition Row
Apartment 50,000 30,000 50,000
building
Office 100,000 -40,000 100,000 100,000
building

Warehouse 30,000 10,000 30,000

NB. Of the three maximum payoffs birr 50,000, birr100,000, and

birr 30,000 the maximum is birr100,000; thus, the
12/06/24 19
Example 2.

Therefore, the developer will select

Residential as the best alternative, since it
provides the highest pay off i.e. 16,000,000.
12/06/24 20
B. Maxi-min criterion (criterion of pessimism)
It is strategy whereby decision maker is identifying the worst (minimum)
payoff for each alternative and then selecting the alternative that has the best
(maximum) of the worst pay off.

Many people view the maxi-min criterion as pessimistic because they

believe the decision maker must assume the worst will occur.

The pessimistic approach/best of the Worst and the decision maker

assumes the worst payoff will occur for each alternative

12/06/24 21
Example 1.
Q. What would be optimum decision as per Maxi-
min criteria?
Sate of natures
Alternatives Good Poor economic Minimum Maximum
economic condition of row of the
condition minimum

Apartment 50,000 30000 30,000 30,000

building

Office 100,000 -40,000 -40,000

building
Warehouse 30,000 10,000 10,000

NB. The maximum of these three minimum

payoffs is 30,000; thus, the decision arrived at by
using the maxi-min criterion would be to
purchase the apartment building.
12/06/24 22
C. Mini-max regret decision criterion
Both the maxi-max and maxi-min strategies can be criticized because
they focus only on a single extreme payoff and exclude the other
payoffs.
This approach does take all payoffs in to account.
In order to use this approach it is necessary to develop an
opportunity loss table.
The opportunity loss reflects the difference between each payoff and
the best possible payoff in a given state of nature

Regret is the difference between the payoff from the best decision
and all other decision payoffs.
Regret = (best payoff) – (actual payoff)

The decision maker attempts to avoid regret or loss by

selecting the decision alternative that minimizes the maximum
regret.
12/06/24 23
Necessary steps for Minimax Regret Criterion Decision
Making
1.Create an opportunity loss table by determining the
opportunity loss from not choosing the best alternative.

2.Opportunity loss is calculated by subtracting each payoff in

the column from the best payoff in the column.

3.Find the maximum opportunity loss for each alternative and

pick the alternative with the minimum number.

 For our example above, the maximum payoff under good

economic conditions is birr 100,000, and the maximum
payoff under poor economic conditions is birr 30,000.

 All other payoffs under the respective states of nature are

subtracted from these amounts, as follows
12/06/24 24
 Regret Table and Values
Alternati Good Poor Maxim Minimu
ves Economic Economic um m of the
Condition Condition Regre maximu
t m
Regret
Apartmen 100,000- 30,000- 50,000 50,000
t 50,000 30,000
=50,000 =0
(Regret) (Regret)
Office 100,000- 30,000-(- 70,000
building 100,000 40,000)
=0 (Regret) =70,000
(Regret)
Warehous 100,000- 30,000- 70,000
e 30,000 10,000
To make the=70,000 =20,000
decision according to the mini-max regret
criterion, the (Regret) (Regret)
maximum regret for each decision must be
determined.
Largest The decision corresponding
100,000 30,000 to the minimum of
these regret values is then selected.
payoff
12/06/24 25
The decision should be to purchase the apartment
building rather than the office building or the warehouse.

This particular decision is based on the philosophy that the

investor will experience the least amount of regret by purchasing
the apartment building.
If the investor purchased either the office building or the
warehouse, birr 70,000 of regret could result; however, the
purchase of the apartment building will result in, birr 50,000 in
regret

12/06/24 26
D. Equally likely criterion /Laplace criterion /principle of
insufficient reason
The equal likelihood, or LaPlace, criterion weights each
state of nature equally, thus assuming that the states of nature
are equally likely to occur/all outcomes equally likely
and uses the average payoff.
The equal likelihood criterion multiplies the decision
payoff for each state of nature by an equal weight.
We calculate the payoffs by assuming all the
states of nature have equal chance of
existence.
12/06/24 27

Example 1
Q. What would be optimum decision as per
equally likely criterion?
Sate of nature
Alternatives Good Poor economic Row
economic condition Weighted
condition Average
Apartment 50000 (0.5) + 30000 (0.5)= 40,000
building

Office 100000 (0.5) -40000 (0.5) 30,000

building +
Warehouse 30000 (0.5) + 10000 (0.5) 20,000

Because birr 40,000 is the highest weighted value, the

investor's decision would be to purchase the apartment
building.
12/06/24 28
 E. Hurwicz criterion
A coefficient of optimism, α, is a measure of the decision
maker's optimism.
The Hurwicz criterion multiplies the best payoff by α and
the worst payoff by 1- α., for each decision, and the best result
is selected
This allows you to choose how much of an optimist or
pessimist you want to be .
Choose a number (α) between 0 (pure pessimist) and 1
(pure optimist).

For each alternative compute a weighted average of the best

and worst outcomes for that alternative : weighted average =
α(best outcome) + (1- α)(worst outcome) Choose the
alternative that has the highest weighted average.
12/06/24 29
The Criterion of Realism decision rule is an attempt to make a tradeoff
between complete risk taker (as in the Maximax rule), and total risk
aversion (as in the Maximin rule).

To do this, you must choose a Coefficient of Realism, called alpha (α),
which is a decimal number between 0 and 1.

 This number provides the emphasis on the optimistic view. The number
(1-α), then, is the amount of emphasis that is placed on the most
pessimistic outcome.

 For example, if a manager chose an alpha of 0.6, he would be placing

60% emphasis on a risky, high return (Maximax-type) outcome, and 40%
emphasis (since 1-0.6 = 0.4 or 40%) on a low-risk, pessimistic,
(Maximin-type) outcome.

12/06/24 30
To determine the decision under the Criterion of Realism
decision rule, a column is added on the right side of the payoff
table.

In this column the decision maker must calculate the factor
by multiplying the best outcome in the row by α, multiplying
the worst outcome in the row by (1-α),and adding the two
result together.

From these calculated numbers in each row, identify the

highest one, and that will be in the row of the decision
alternative to be selected under this rule.

12/06/24 31
In the example above, the manager decided to use an alpha
of 0.8, meaning that he wanted to place 80% emphasis on a
high-payoff alternative, and so only 20% emphasis on the
low-risk alternative.

Since the decision alternative Construct a Large

Plant has the maximum payoff in the new Criterion of
Realism column, it would be selected as the decision to
implement. 12/06/24 32
4.2.2.3. Decision Making Under Risk
Environment
 The essential difference between decision making under complete
uncertainty and decision making under Risk (partial uncertainty) is the
presence of probabilities for the occurrence of the various states of
nature in partial uncertainty.
 The probabilities may be subjective estimates from managers or from
experts in a particular field or they may reflect historical frequencies.
 If they are reasonably correct they provide a decision maker with
additional information that can dramatically improve the decision
making process.
 The decision maker has some knowledge or experience which will
enable him to assign probabilities to the occurrence of each state of
nature.
 The objective is to optimize the expected profit or to minimize the
opportunity loss.
12/06/24 33
Methods to make decision under risk
 EMV (Expected monetary value) criterion,

 EOL ( expected Opportunity loss) criterion

 EVPI ( expected value of perfect information)

12/06/24 34
A. EMV (Expected monetary value) criterion,
Steps:
1,The decision maker must first estimate the probability of occurrence of
each state of nature.
2,Then, the expected value is computed by multiplying each outcome (of a
decision) by probability of its occurrence.
3,Max EMV will be selected
Example 1: Let probability that Good economic condition 0.6 and 0.4 of poor
economic condition

 EMV for Apartment Building: 50, 000 (0.6) + 30, 000(0.4) = 42, 000
Office Building : 100, 000 (0.6) - 40, 000(0.4) = 44, 000
Ware House : 30, 000 (0.6) +10, 000(0.4) = 22, 000
The best decision is the one with greatest expected value. Because the
greatest expected value is to purchase the office building.

12/06/24 35
Example 2:
Considering the real estate development problem, assuming the manager
estimates the state of nature as Low Economic Growth: 20%, Medium
Economic Growth: 50% & High Economic Growth: 30%.

We can compute the expected monetary value for the real state developer’s
alternatives as follows
20% 50% 30%
EMVR= 0.2 (4) + 0.5 (16) + 0.3(12) = 12.40
EMVHT=0 .2 (5) + 0.5 (6) + 0. 3(10) = 7.00
EMVHS=0.2 (-1) + 0.5 (4) + 0.3(15) = 6.30

Because the residential alternative has the largest expected monetary value,
it would be selected using this criterion

12/06/24 36
B. EOL ( expected Opportunity loss) criterion or

 The expected opportunity loss is the expected value of the

regret for each decision or it is the cost of not picking the
best solution.
 The expected monetary value and expected opportunity loss
criterion result in the same decision.

Steps Required EOL Criterion

1. First construct an opportunity loss table
2. Multiply the opportunity loss by the probability of that loss
for each possible outcome and add these together.
3. Select alternative that led to minimum EOL

12/06/24 37
Example: What would be optimum decision as
per EOL criterion?

Alternative Good Poor EOL

s Economic Economic
Apartme 100,000-50,000 30,000-30,000 50,000(0.6)+0(
=50,000 (OL) =0 (EOL) .4)
nt =30,000
Office 100,000- 30,000-(- 0(.6)+70000(.4
100,000 40,000) )
=0 (OL) =70,000 (OL) =28,000
Warehou 100,000-30,000 30,000-10,000 70,000(0.6)+2
NB. The best=70,000
decision is
(OL)a decision which
=20,000 (OL) minimize the regret
0000(0.4)=50,
se 000
or loss, because 28000 is the min expected regret, the decision
Probability 60% 40%
maker is to purchase the office building.

12/06/24 38
Example 2.
For real estate problem, the expected opportunity loss can be calculated as
follows (use previously calculated opportunity loss table)

EOLR = 0.2(1) +0.5(0) +0. 3(3)= 1.10

EOLHT = 0.2(0) +0.5(10) + 0.3(5)= 6.5
EOLHT = 0.2(6) +0.5(112) +0. 3(0)= 7.2

Because the residential alternative has the minimum expected opportunity

loss, it would be selected

12/06/24 39
C. Expected Value of Perfect Information (EVPI)

 The expected value of perfect information (EVPI) is the

maximum amount a decision maker should pay for additional
information.
 EVPI equals the expected value (with) given perfect
information minus the expected value calculated without
perfect information.

 EVPI=EVwPI-EMV…….computed without perfect

information=EOL

 EVPI equals the expected opportunity loss (EOL) for the best
decision.
12/06/24 40
 It can sometimes be useful for a decision maker to determine the potential benefit of knowing
for certain which state of nature is going to prevail.

The expected value of perfect information (EVPI) is a measure of the difference between the
certain payoff that could be realized under a condition of certainty and the expected under
conditions involving risk.

 Consider the payoff that the real estate developer could expect under certainty.
If the developer knew that the economic growth is low, the hospital
alterative would be chosen with a payoff of 5, 000,000.
If the developer knew a medium economic growth would exist, the
residential alternative would be chosen for a payoff of 16,000,000 and
if the developer knew that a high economic growth would happen, hotel
would be chosen for a payoff of 15,000,000.
Hence if it were possible to remove the uncertainty surrounding the states of nature, the decision
maker could capitalize on that knowledge.

Obviously before investing time or money in eliminating the probabilities, it will be impossible
for the decision maker to say which states of nature will turn out to be the one that will occur.

12/06/24 41
Decision with Perfect
Information
Alternatives Good Poor Maximu
Economic Economic m
Apartment 50,000 30,000

Office 100,000 -40,000

Warehouse 30,000 10,000

Decision
Probability with perfect
60% information:
40%
Perfect Information 100000 30000
EVwPI=Perfect 100000(0.6)+ 30000(0.4) 72,000
*Probability =
Best EMV see slide 41 44,000
EVPI=EOL=EVwPI-EMV =28,000
72,000-44,000
12/06/24 42
DECISION TREES
Any problem that can be presented in a decision
table can also be graphically represented in a
decision tree and it is most beneficial when a
sequence of decisions must be made.

Can be used instead of a table to show

alternatives, outcomes, and pay offs

Thus, decision tree is a diagram consisting of square,

circle probability nodes, and branches representing
decision alternatives.

12/06/24 43
Steps in Decision Tree Analysis

1.Define the problem.

2. Structure or draw the decision tree.

3.Assign probabilities to the states of nature.

4.Estimate payoffs for each possible combination of alternatives and states of

nature.

5.Solve the problem by computing expected monetary values (EMVs) for

each state of nature node.

12/06/24 44
Expected value computed at each node
Example, Office (node 3)= 100000(0.6)-40000(0.4)=
44000

Expected value computed at each node

Example, apartment (node 2)= 50000(0.6)+30000(0.4)= 42000
12/06/24 45