DECISION THEORY

Thousands of business decisions are made every day and not all will MAKE or BREAK
the organization. But each one adds a measure of success (or failure) to the operations, i.e. all
decisions have some influence- large or small- on performance. e.g An electronics manufacturer
must decide whether to invest in a new process or to stay with a proven one that is producing
defective chips at a rate of 1 in 3.

Does the ability to make good decisions come naturally or it can be learned? Management
scientists hold that education, scientific training, and experience can improve a persons ability
to make decisions. The idea of management as a science is founded on its similarity to other
sciences as expressed below.
Organized principles of knowledge,
Use of empirical data,
Systematic analysis of data,
Repeatable results.
Business decision makers have always had to work with incomplete and uncertain data. In some
situations a decision maker has (or is assumed to have) complete information about the decision
variables; at the other extreme no information available. Managerial decisions are made all
along this continuum.

The Six Steps in Decision Theory:

1. Clearly define the problem.
2. List the possible alternatives.
3. Identify the possible outcomes or states of nature.
4. List the payoff or profit of each combination of alternatives and outcomes.
5. Select one of the mathematical decision theory models.
6. Apply the model and make your decision.

Types of Decision Making Environments:

Type 1: Decision Making Under Certainty (We already know)
In the environment of decision making under certainty, decision makers know
with certainty the consequence of every alternative or decision choice. Naturally,
they will choose the alternative that will maximize their well-being or will result
in the best outcome.

Type 2: Decision Making Under Uncertainty (Probability is not given)

In decision making under uncertainty, there are several possible outcomes for
each alternative, and the decision maker does not know the probabilities of the
various outcomes.
In this environment, probability is not given. So we have the five situations under
which we can make decisions
A. Criterion of pessimism (Maximin or Minimax)
This criteria is based on the conservative approach to assume that, the
worst possible is going to happen. The decision maker considers each
 strategy and locates the minimum pay off for each and then selects that
alternative which maximise the minimum pay off. This is known as
maximin criterion Thus, this criterion involves two steps.
Step I Find the minimum assured pay off for each alternative (course
of action)
Step II Choose that alternative which corresponds to the maximum of
the above minimum pay off

When dealing with the cost, the maximum cost associated with each
other alternative is considered and the alternative that minimise this
maximum cost is chosen. This is known as minimax criterion and it
involves two steps.
Step I Determine the maximum possible cost for each alternative.
Step II Choose that alternative which corresponds to the minimum of
the above costs.

B. Ceriterion of optimism (Maximax or minimin )

This criterion is based on extreme optimism. In this criterion, the
decision maker ensures that he should not miss the opportunity to
achieve the greatest possible pay off or lowest possible cost.

In maximax criterion, the decision maker selects that particular

strategy which corresponds to the maximum pay off for each strategy.
Thus, the maximax criterion consists of the following two steps

Step I Determine the maximum possible way off for each alternative.
Step II Select that alternative which corresponds to the maximum of the
above maximum pay offs.

In the decision problems dealing with costs, the minimum for each
alternative is considered and then the alternative which minimizes the
above minimum cost is selected. This is termed as minimin principle. This
is known as minimin criterion and it involves two steps.

Step I Determine the minimum possible way off for each alternative.
Step II Select that alternative which corresponds to the minimum of the
above minimum pay offs.

C. Laplace Criterion (equally likely decision criterion)

This criterion is based on, what is known as the principle of
insufficient reason. Since the probabilities associated with the
occurrence of various events are unknown, there is not enough
information to conclude that these probabilities will be different.
Hence it is assumed that all states of nature will occur with equal
probability. That is, each state of nature is assigned an equal
probability. As states of nature of mutually exclusive and collectively
exhaustive, the probability of each of these must be 1/(number of
states of nature).
 This criterion involves following steps.
Step I Assign equal probabilities 1/(number of states of nature) to each
pay off a strategy.
Step II Determine the expected pay off value for each alternative
Step III Select that alternative which corresponds to the maximum (and
minimum for cost) of the above expected expected pay offs.

D. Hurwicz criterion (Criterion of Realism)

This criterion suggests that a rational decision maker should neither be
completely optimistic nor be pessimistic and therefore, must display a
mixture of both. Hurwicz, who suggests this criterion, introduced the
idea of a coefficient of optimism (denoted by ) to measure the
decision makers degree of optimism. This coefficient lies between 0
and 1, where 0 represents a completely pessimistic attitude about the
future and 1, completely optimistic attitude about the future.The
working procedure is-
Step 1: Decide the coefficient of optimism and then the coefficient
of pessimism (1-).
Step 2:Determine the maximum as well as minimum pay off for each,
alternative and obtain the quantities.

H = (maximum of each alternative) + (1-) (minimum of each alternative)

Step 3: Select an alternative with value of H as maximum. For =1,

the Hurwicz criteria is equal to the maximin or minimax
criteria. For = 0, it is equal to maximax or minimin criteria.

E. Savage Criterion (criterion of regret, minimax regret criterion,

opportunity loss decision criterion)
While the above criterions do not take into account the cost of
opportunity loses by making the wrong decision, the Savage criterion
does so. The savage criterion is based on the concept of regret (or
opportunity loss) and calls for selecting the course of action that
minimises the maximum regret. This criterion is assume that decision
maker feels regret after adopting a wrong course of action (alternative)
resulting in an opportunity loss of pay off.
Step I From the given pay off matrix, develop an opportunity loss (or
regret) matrix
(a) Find the best pay off corresponding to each state of nature
(maximum for profit and minimum for cost)
(b).ith regret =( maximum pay off ith pay off) for jth event if the
pay offs represent profits = (minimum pay off ith pay off)
for jth event if the pay offs represent costs.
Step II Determine the maximum regret amount for each alternative.
Step III Choose that alternative which corresponds to the minimum
regrets.
Type 2: Decision Making Under Risk (Probability is given)
In decision making under risk, there are several possible outcomes for each
alternative, and the decision maker knows the probability of occurrence of each
outcome. The decision maker usually attempts to maximize his or her expected
well-being. Decision theory models for business problems in this environment
typically employ two equivalent criteria: maximization of expected monetary
value and minimization of expected loss.

In decision making under risk probabilities are given. That means we are aware of
success or failure of decision to some extent. We select the alternative with the
highest expected value. We also use the probabilities with the opportunity loss
table to minimize the expected opportunity loss. In decision making under risk,
we will discuss about Expected Monetary Value, Expected Value of Perfect
Information, and Expected Opportunity Loss.

a. Expected Monetary Value

The EMV means the long run average value of that would result if the decision
were repeated a large number of times. The EMV for an alternative is just the sum
of possible payoffs of the alternatives, each weighted by the probability of that
payoff occurring.

We can calculate EMV with the following formula.

EMV (alternative i) = (Payoff of first state of nature) X (probability of
first state of nature) + (Payoff of second state of nature)
X (probability of second state of nature) + ..(Payoff of
i state of nature) X (probability of i state of nature)

b. Expected Value Of Perfect Information (EVPI)

It places an upper bound on what you should be willing to spend on information.
It is the increase in Expected Monetary Value. The formula is:
EVPI = expected profit with perfect information maximum EMV

Expected Value with Perfect Information (EPPI)

It is the expected or average return, in the long run, if we have perfect
information before a decision has to be made.
The formula is:
EPPI = (best payoff for first state of nature) X (probability of first
state of nature) + (best payoff for second state of nature) X
(probability of second state of nature) ++ (best payoff for i
state of nature) X (probability of i state of nature)

c. Expected Opportunity Loss

The alternative approach to maximizing the EMV is to minimize expected
opportunity loss. Opportunity cost, sometimes called regret, refers to the
difference between the optimal profit or payoff for a given state of nature and
the actual payoff received.
 In other words, its the amount lost by not picking the best alternative in a
given state of nature.

First, we will construct opportunity loss table by determining the opportunity

loss for not choosing the best alternative for each state of nature.

DECISION TREES
In some cases, the choice of the optimal act is not made in one stage, and the decision problem
involves a sequence (not necessarily in time) of acts, events, acts, events, etc. There may be a
number of basic alternatives, each leading to one of a number of situations depending on the
outcome of a certain random process. At each such situation, a number of other alternatives may
be available which also lead to a new set of situations depending on another set of events... and
so on, with acts followed by events, followed by acts, events, etc. The sequence of acts and
events may be depicted in the form of a decision tree. The decision problem is to find the most
preferred branch of that tree.

A decision tree is a graphical model describing decisions and their possible outcomes. Decision
trees consist of three types of nodes:
1. Decision node: Often represented by squares showing decisions that can be made.
Lines emanating from a square show all distinct options available at a node.
2. Chance node: Often represented by circles showing chance outcomes. Chance
outcomes are events that can occur but are outside the ability of the decision maker to
control.
3. Terminal node: Often represented by triangles or by lines having no further decision
nodes or chance nodes. Terminal nodes depict the final outcomes of the decision making
process.
ANALYSIS OF DECISION TREE:
The general approach used in the decision tree analysis is the Roll Back Process, i.e.
here we move from right to left. The expected return (Expected Monetary Value, EMV)
is calculated at each node starting from the extreme right node. If it is a chance node then
EMV of this node is the sum of the products of the respective payoffs. The expected
return (EMV) of a decision node is the maximum EMVs along all decision branches
emanating this decision node. Thus starting from the extreme right we move along the
path that yields the maximum pay-off (EMV) for each of the decision.

STEPS IN DECISION TREE ANALYSIS

For the solution of a multistage problem, by decision tree analysis, stepwise procedure is
as follows:
Step 1: Construct the decision tree representing all decision points, possible course
of action, states of nature.
Step 2: At each decision point determine the probability and the payoffs associated
with each course of action and show in the diagram at appropriate places.
Step 3: Starting from extreme right end, compute the expected payoffs (EMV) for
each course of action.
Step 4: Select the course of action that yields the best expected payoff (EMV) for
each of the decisions.
Step 5: Proceed backwards to the next decision point.
Step 6: Repeat the step 3 and step 4, till the first decision point is reached.
Step 7: Finally select that course of action from the extreme right to left which
yields the maximum possible EMV at the first decision point.