DECISION THEORY

1. Introduction :

Decisions in business may be classified into two categories,

tactical and strategic.

Tactical decisions are those which affect the business in short

run.

Strategic decisions are those which have far reaching effect

on the course of business.
The decision making problems can be discussed
under following headings :

• Decision making under certainty

• Decision making under uncertainty
• Decision making under risk
• Decision making under conflict
1. Decision making under certainty :

In this case, the decision maker presumes that only one

state of nature is relevant for his purpose.
2. Decision making under uncertainty :
When decision maker faces multiple states of nature
but he has no means to arrive at probability values to
the likelihood of occurrence of these states of nature,
the problem is a decision problem under uncertainty.

Such situations arise when new product is introduced

in the market or a new plant is set up. Here, the
choice of decision largely depends on the personality
of the decision maker.

The following choices are available before the

decision maker in situations of uncertainty.
(a) Maximax Criterion
(b) Minmax Criterion
(c) Maxmin Criterion
(d) Laplace Criterion
(a) Maximax Criterion :
The term 'maximax' is an abbreviation of the phrase
maximum of the maximums, that would result in the
maximum payoff possible.

Suppose for each action there are three possible

payoffs corresponding to three states of nature as given
in the following decision matrix :

Maximum under each decision are (220, 190, 200). The

maximum of these three maximums is 220.
Consequently according to the maximax criteria the
decision to be adopted is A1
(b) The minimax decision criterion
Minimax is just the opposite of maximax. Application
of the minimax criteria requires a table of losses
instead of gains. The losses are the costs to be
incurred or the damages to be suffered for each of the
alternative actions and states of nature. The minimax
rule minimizes the maximum possible loss for each
course of action.
It shows that the maximum losses incurred by the
various decisions
A1 A2 A3
18 14 10
and the minimum among three maximums is 10 which
is under action A3. Thus according to minimax criterion,
the decision-maker should take action A3
(C) The maximin decision criterion (Criterion of
pessimism) :
The maximin criterion of decision making stands for
choice between alternative courses of action as
summing pessimistic view of nature. Taking each act in
turn, we note the worst possible results in terms of
payoff and select the act which maximizes the minimum
payoff.

Minimum under each decision are respectively

-80 -60 -20
The action A3 is to be taken according to this criterion
because it's -the maximum among minimums.
(d) Laplace Criterion :

As the decision maker has no information about the

probability of occurrence of various events, the decision
maker makes a simple assumption that each probability
is equally likely.

The expected payoff is worked out on the basis of

these probabilities. The act having maximum expected
pay off is selected.
Problem 1 :
 Solution
We associate equal probability for each event say 1/3.
Expected payoff are

Since A3 has maximum expected payoff, A3 is the

optimal Act.
3. Decision making under risk :
In this situation the decision maker has to face
several states of nature. But he has some knowledge
or experience which will enable him to assign
probability to the occurrence of each state of nature.
The objective is to maximize the expected profit, or to
minimize the opportunity loss.

For decision problems under risk, the most popular

methods used are :
(1) Expected Monetary Value (EMV) Criterion
(2) Expected Opportunity Loss (EOL) Criterion
(3) Expected Value of Perfect Information (EVPI)
Criterion
1. Expected Monetary Value (EMV) Criterion :

When the probabilities can be assigned to the various

states of nature, it is possible to calculate the statistical
expectation of gain for each course of action. The
conditional value of each event in the pay off table is
multiplied by its probability and the product is summed
up. The resulting number is the EMV for the act.

The decision maker then selects from the available

alternative actions, the action that leads to the
maximum expected gain (that is the action with
highest EMV).
Example : Let the states of nature be S1 and S2 and the
alternative strategies be A1 and A2.
Pay off table :

Let the probabilities for the states of nature S1 and S2

be respectively 0.6 and 0.4.

Then, EMV for A1 = (30 x 0.6) + (35 x 0.4) =

18 + 14 = 32

EMV for A2 = (20 x 0.6) + (30 x 0.4) = 12 + 12 = 24

:. EMV for A1 is greater.
:. The decision maker will choose the strategy A1
2. Expected Opportunity Loss (EOL) Criterion :

The difference between the greater payoff and the

actual payoff is known as opportunity loss.

Under this criterion the strategy which has minimum

Expected Opportunity Loss (EOL) is chosen.

The calculation of EOL is similar to that of EMV.

 Example: Given below is an opportunity loss table. A1
and A2 are the strategies and S1 and S2 are the states of
nature.

Let the probabilities for two states be 0.6 and 0.4

EOL for A1 = (0 x 0.6) + (2 x 0.4) = 0.8
EOL for A2 = (10 x 0.6) + (-5 x 0.4) = 6 – 2 = 4

EOL for A1 is least. Therefore the strategy A1 may be

chosen.
3. Expected Value of Perfect Information (EVPI)
Criterion :
The expected value with perfect information is the
average (expected) return in the long run, if we have
perfect information before a decision is to be made.

In order to calculate EVPI, we choose the best

alternative with the probability of their state of nature.

The expected value of perfect information (EVPI) is the

expected outcome with perfect information minus the
outcome with max EMV.

.'. EVPI = (Expected payoff with perfect information -

max. EMV)

Expected Monetary Value = (EMV)

Example 3 :
A1 A2, A3 are the acts and S1, S2, S3 are the states of
nature. Also known that P(S1) = 0.5, P(S2)= 0.4 and
P(S3) = 0.1
Solution :
Pay off table :

EMV for A1 = {0.5 x 30) + (0.4 x 20) + (0.1 x 40) =

15+8+4 = 27
EMV for A2 = (0.5 x 25) + (0.4 x 35) + (0.1 x 30) =
12.5+14+3 = 29.5
EMV for A3 = (0.5 x 22) + (0.4 x 20) + (0.1 x 35) = 11+
8+3.5 = 22.5
The Maximum EMV is for the strategy A2 and it is 29.5
Now to find EVPI, workout expected value for maximum
payoff under all states of nature.
.'. Expected payoff with perfect information = 33

:. Thus the expected value of perfect information

(EVPI) = Expected pay-off with Perfect Information -
Maximum EMV = 33 - 29.5 = 3.5
Example 4 :
You are given the following pay-offs of three acts A1, A2
and A3, and the states of nature S1, S2 and S3.

The probabilities of the states of nature are respectively,

0.1, 0.7 and 0.2. Calculate and tabulate the EMV and
conclude which of the acts can be chosen as the best.
Solution :
 Example 5 :
A management is faced with the problem of
choosing one of the products for manufacturing. The
probability matrix after market research for the two
products was as follows.

The profit that the management can make for

different levels of market acceptability of the products
are as follows.

Calculate expected value of the choice of alternatives and advise

the management.
 Let us put the above information in a payoff matrix with
probabilities associated with the states of nature.

Since the expected pay off (EMV) of product B is

greater, product B should be preferred by the
management.
Preparation of payoff table :
Example 6 :
A small ink manufacturer produces a certain type of ink
at a total average cost of Rs. 3 per bottle and sells at a
price of Rs. 5 per bottle. The ink is produced over the
week-end and is sold during the following week.
According to the past experience the weekly demand
has never been less than 78 or greater than 80 bottles
in his place. You are required to formulate pay off table.
Solution :
The different states of nature are the demand for 78
units, 79 units or 80 units. Call them S1, S2, S3,
The alternative courses of action are selling 78 units, 79
units or 80 units. Call them A1, A2, A3.
Selling price of ink= Rs. 5/- per bottle
Cost price = Rs. 3/- per bottle
Calculation of pay-offs (Pay off stands for the gain)
Sale quantity x price - Production quantity x Cost
(Explanation: S1.A1 means selling quantity is 78 and
manufacturing quantity is 78. S1.A2 means sales 78,
production 79 and so on.)

Note: We shall show the states of nature in rows and

acts in columns.
Preparation of loss table :
Example 7
A small ink manufacturer produces a certain type of ink
at a total average cost of Rs.3 per bottle and sells at a
price of Rs. 5 per bottle. The ink is produced over the
week-end and is sold during the following week.
According to the past experience the weekly demand
has never been less than 78 or greater than 80 bottles
in his place.
You are required to formulate the loss table.
 Solution
 Calculation of regret (opportunity loss) :
 A1S1 = 0 (since production and sales are of equal quantity
say 78)
 A2S1 = 1x 3 = 3 (since one unit of production is in excess
whose cost = Rs.3)
 A3S1= 2 x 3 = 6 (since 2 units of production are in excess
whose unit cost is@ Rs. 3)
 A1S2 = 1x 2 = 2 (since the demand of one unit is more
than produced, the profit for one unit is Rs.2)
 Similarly A2S2 = 0 (since units of production = units of
demand)
 A3S2 =1 x 3 = 3
 A1S3 = 2 x 2 = 4
 A2S3 = 2 x 1 = 2 and A3S3 = 0
 From the pay off table also opportunity
loss table can be prepared.

 Method: Let every row of payoff table represent a state

of nature and every column represent a course of action.
Then from each row select the highest payoff and subtract
all payoff of that row from it. They are the opportunity
losses.
 A newspaper boy has the following probability
of selling a magazine :

Cost of a copy is 30 paise and sale price is 50 paise. He

cannot return unsold copies. How many copies should
he order?
 We can apply either EMV criterion or EOL
criterion. Let us apply EMV criterion for which
we have to calculate payoff. Number of copies
ordered is the different courses of action. The
copies ordered may be 10, 11, 12, 13, 14. Denote
them by A1, A2, A3, A4, A5.
 Similarly number of copies demanded may be 10,
11, 12, 13 or 14. These demands may be D1, D2,
D3, D4, D.5 These are events. The pay-off values
are calculated below :
 Selling price of each item = 50 Ps. and cost of a
copy = 30 Ps.
 :. EMV for the Acts A1, A2, A3, A4, and
A5 are respectively 200, 215, 222.5, 220
and 205.
 EMV for A3 is greater and therefore A3
 is optimal act.
 :. No. of copies to be ordered = 12