Chapter 4

Decision Theory Model

23/02/21 1
 Introduction
• Brainstorming question
• Why do some organizations succeed
and some others fail?

23/02/21 2
 Decision theory (cont’d)
• Making of a decision requires enumeration of
feasible and viable alternatives, the consequences
associated with different alternatives, and
measure of effectiveness by which the most
preferred alternative is identified.
• Decision theory provides an analytical and
systematic approach to the study of decision
making.
• It provides a method of natural decision making
wherein data concerning the occurrence of
different outcomes may be evaluated to enable
the decision maker to identify suitable
alternative.
23/02/21 3
 Decision theory (cont’d)
• Decision models useful in helping
decision makers make the best
possible decisions are classified
according to the degree of certainty.
The scale of certainty can range
from complete certainty to complete
uncertainty. The region which falls
between this two is decision making
under risk or probabilistic problems.
23/02/21 4
Some important terminologies
• Decision alternatives- courses of action,
acts, or strategies and are under the
control of the decision maker and known
to the decision maker
• State of nature- A possible future
condition resulting from the choice of the
decision. States of nature are mutually
exclusive and collectively exhaustive.
• Payoff- A numerical value resulting from
each possible combination of alternatives
and state of nature is called the payoffs
23/02/21 5
 Steps in decision making
• Decision making process involves the
following steps
– Identify and define the problem
– Listing of possible future events which can
occur in the context of the decision problems
– Identification of all the courses of action which
are available to the decision maker
– Expressing the payoffs resulting from the pair
of state of nature and alternative courses of
action
– Apply an appropriate mathematical decision
theory model to select the best course of
action from the given list on the basis of some
criteria that results in the optimal payoff.

23/02/21 6
 Decision making environment
• Decision making under certainty
• Decision making under risk
• Decision making under uncertainty
• What do they mean?

23/02/21 7
 Decision making under
uncertainty
• In the absence of knowledge about the
probability of any state of nature
occurring, the decision maker must arrive
at decision only on the actual conditional
payoff values, together with the policy.
• There are several different criteria of
decision making uner such situation:
– Maximax
– Maximin
– Equally likely/laplace
– Criterion of realism
– Criterion of regret

23/02/21 8
 Criterion of optimism
• The decision maker ensures that he should not
miss the opportunity to achieve the largest
possible profit (maximax) or lowest possible cost
(minimin). Thus he selects the alternative that
represents the maximum of the maximums or
minimum of minimums.
• Since this criterion selects the alternative with
the largest payoff value, it is called an optimism
decision criterion. The method is summarized as
follows:
– Select the maximum payoff value corresponding to each
alternative
– Select the alternative with largest anticipated pay of
value

23/02/21 9
 Criterion of pessimism
• The decision maker ensures that he would earn no
less than or pay no more than some specified amount.
He selects the alternative that represents the
maximum of the minima (minimum of the maxima
in case of lose) pay off in the case of profits. The
method can be summarized as;
• Locate the minimum pay off value in the case of loss
and maximum in the case of profit corresponding to
each alternative course of action
• Select an alternative with the best anticipated payoff
value
• This criterion is conservative about the future and
always anticipates the worst possible outcome. It is
called pessimistic decision criterion or weld’s criterion.

23/02/21 10
 Equally likely decision (laplace)
criterion
• Some probabilities of state of nature are not
known and there fore it is assumed that all
states of nature is assigned an equal probability.
As states of nature are mutually exclusive and
collectively exhaustive, the probability of each of
these must be one divided by number of states of
nature. The working method is summarized as
follows.
– Assign equal probability value to each state of nature
– Compute the expected payoff for each alternative as
∑PjPij
– Select the best expected payoff
– This criterion is also called the criterion of insufficient
reason

23/02/21 11
 Criterion of realism (Hurwicz
criterion)
• This suggests that rational decision maker should not be neither
completely optimistic of pessimistic; therefore, must display a
mixture of both. Hurwicz introduced the concept of a coefficient
of Optimism to measure the decision maker’s degree of optimism.
This coefficient lies between 0 and 1 where 0 represents complete
pessimistic and 1 represents complete optimistic attitude about
the future. Thus, α shows degree of optimism and 1- α shows the
coefficient of pessimism.
• Hurwicz approach suggests that the decision maker must select
the alternative that maximizes:
CR of an Alternative = (α) (maximum in the row) + (1 minus α)
(minimum in the row)
• The method can summarized as:
–Decide the coefficient of optimism
–For each alternative select the largest and the lowest payoff value and
multiply it with the coefficient of optimism and the coefficient of
pessimism respectively and calculate the weighted average.
–Select the alternative with the largest anticipated weighted average
payoff.

23/02/21 12
 Criterion of regret
• It is also called opportunity loss decision criterion
or minimax regret decision criterion because
decision maker feels regret after adopting a
wrong course of action resulting from resulting
In an opportunity loss of payoffs. Thus he always
intends to minimize this regret. The method can
summarized as:
• From the given payoff matrix develop an
opportunity loss matrix as follows
– Find the best payoff corresponding to each sate of
nature
– Subtract all other entries in that row from this value
– For each course of action, identify the worst or
maximum regret value
– Select the course of action with the smallest anticipated
opportunity loss value

23/02/21 13
 Illustration

Payoff table
Decision State of demand
alternatives High Medium Low

Apartment bldg. 100,000 70,000 25,000

Office bldg. 50,000 40,000 30,000
Warehouse bldg. 150,000 25,000 (30,000)
 Decision making under risk
• The essential difference between decision
making under complete uncertainty and
decision making under partial uncertainty
is the presence of probabilities for the
occurrence of the various states of nature
under partial uncertainty.
• The term risk is often used in conjunction
with partial uncertainty.
• The probabilities can be subjective
estimates form managers or experts or it
can be the reflection of historical
frequencies. The sum of the probabilities of
all states of nature must be 1.

23/02/21 15
 Decision making criteria

• Expected monetary value

• Expected opportunity loss
• Expected value of perfect
information

23/02/21 16
 State of nature

Decision Strong demand Weak demand

alternative P= 0.8 P= 0.2
Small complex 8 7

Medium complex 14 5

Large complex 20 -9

23/02/21 17
 Illustration

Payoff table
Decision State of demand
alternatives High (0.5) Medium(0.3) Low(0.2)

Apartment bldg. 100,000 70,000 25,000

Office bldg. 50,000 40,000 30,000
Warehouse bldg. 150,000 25,000 (30,000)
 Expected monetary value
• provides the decision maker with a value
which represents an average payoff for
each alternative.
• The best alternative is the one that has
highest expected monetary value.
• The average or expected payoff of each
alternative is a weighted average: the
state of nature probabilities are used to
weight the respective payoffs (long run
average amount one could reasonably
anticipate
23/02/21 19
 Expected opportunity loss
• An alternative method to incorporate
probabilities in to decision is to use expected
opportunity loss.
• The approach is nearly identical to the EMV
approach provided that the table of
opportunity loss is used rather than the table
of payoffs.
• Hence opportunity losses are weighted by the
probabilities of their respective states of
nature to compute a long run average
opportunity loss, and the alternative with
the smallest expected loss is selected
(Opportunity loss results in the alternative as
EMV approach).

23/02/21 20
 Expected value of perfect
information
• It can sometimes be useful for decision maker
to determine the potential benefit of
knowing for certain which state of nature is
going to prevail.
• It is the measure of the difference between
certain payoff that could be realized under a
condition of certainty and expected payoff
under condition involving risk.
• The expected value of perfect information
presents an upper bound on the amount of
money that the decision maker would be
justified to spend to obtain perfect
information

23/02/21 21
 Expected value of perfect
information
• It is, however, not always possible to remove
uncertainties utterly.
• In such cases the decision maker must weigh
the cost to reduce uncertainty (obtain better
estimates of probabilities) against the
expected benefits that would result from the
improved estimation.
• EVPI is exactly equal to EOL. The EOL
indicates the expected opportunity loss due
to imperfect information which is equal to
the expected payoff of the perfect
information.

23/02/21 22
 P (strong d= 0.8)
• EMV 1= 7.8
EOL1= 12(0.8)= 9.6
• EMV 2= 12.2 EOL2= 6(0.8) + 2(0.2) =5.2
EOL3= 16(0.2) =3.2
• EMV 3= 14.2
EVWPI= 20*0.8+7*0.2= 17.4

EVPI=EVWPI-EMV=17.4-14.2=3.2

23/02/21 23