DECISION ANALYSIS o The rows correspond to the

possible decision alternatives.

Guide questions
o The columns correspond to the
 What factors will influence your possible future events.
decision? o Events (states of nature) are
 How certain are you that these factors mutually exclusive and
will exist? colelctively exhaustive.
 A method for reducing uncertainty in o The table entries are the
the decision making process through payoffs.
data analysis.
EXAMPLE
 Provides a rational process for making
decisions that is far better than random  Franz Coquilla has inherited $1,000.00
selection.  He has to decide how to invest the
 Easy to update if conditions change. money for one year.
 The field of decision analysis provides a  A broker has suggested five potential
framework for making important investments.
decisions o Gold
 Decision analysis allows us to select a o Junk Bond
decision from a set of possible decision o Growth Stock
alternatives when uncertainties o Certificate of Deposit
regarding the future exist. o Stock Option Hedge
 The goal is to optimize the resulting  The return on each investment depends
payoff in terms of a decision criterion. on the (uncertain) market behavior
Five Steps in Decision Making during the year.
 Franz would build a payoff table to help
1. Clearly define the problem make the investment decision.
2. List all possible alternatives
3. Identify all possible outcomes for each PAYOFF TABLE
alternative  Construct a payoff table.
4. Identify the payoff for each alternative o Select a decision-making
& outcome combination criterion and apply it to the
5. Use a decision modeling technique to payoff table.
choose an alternative  Identify the optimal decision
Payoff Table Analysis  Evaluate the solution

 Payoff table analysis can be applied

when:
o There is a finitite set of discrete
decision alternatives.
o The outcome of a decision is a
function of a single future
event.
 In a Payoff Table-
  The consequence of every alternative is
known
 Usually there is only one outcome for
THE PAYOFF TABLE each alternative
 This seldom occurs in reality

Decision Analysis: DECISION MAKING UNDER

UNCERTAINTY

 The decision criteria are based on the

decision maker’s attitude toward life.

The criteria includes:

 Maximin Criteria – pessimistic or

conservative approach.
 Minimax Regret Criterion – pessimistic
or conservative approach.
 Maximax Criterion – optimistic or
aggressive approach.
 Principle of insufficient Reasoning – no
information about the likelihood of the
various states of nature.

Decision Making Under Uncertainty – THE

MAXIMIN CRITERION

 This criterion is based on the WORST-

CASE SCENARIO.
o It fits both a pessimistic and a
DECISION MAKING CRITERIA conservative decision maker’s
styles.
 Decision making under certainty. o A pessimistic decision maker
o There future of state-of-nature
believes that the worst
is assumed known. possible result will always
 Decision making under uncertainty. occur.
o There is no knowledge about o A conservative decision maker
the probability of the states of wishes to ensure a guaranteed
nature occurring. minimum possible payoff.
 Decision making under risk.
o There is some knowledge of the
probability of the states of
nature occurring.

Decision Analysis: DECISION MAKING UNDER

CERTAINTY
Decision Making Under Uncertainty – THE
MINIMAX REGRET CRITERION

 This criterion fits both a pessimistic and

a conservative decision maker
approach.
 The payoff table is based on “lost
opportunity,” or “regret”.
Decision Making Under Uncertainty – THE
 The decision maker incurs regret by
MAXIMAX CRITERION
failing to choose the “best decision”.
 To find an optimal decision, for each  This criterion is based on the best
state of nature: possible scenario. It fits both an
o Determine the best payoff optimistic and an aggressive decision
overall decisions. maker.
o Calculate the regret for each  An optimistic decision maker believes
decision alternative as the that the best possible outcome will
difference between its payoff always take place regardless of the
value and this best payoff value. decision made.
o For each decision find the  An aggressive edcision maker looks for
maximum regret over all states the decision with the highest payoff
of nature. (when payoff is profit).
o Select the decision alternative
that has the minimum of these
“maximum regrets”.
Decision Making Under Uncertainty – THE
PRINCIPLE OF INSUFFICIENT REASON

 This criterion might appeal to a decision

maker who is neither pessimistic nor
optimistic.
 It assumes all the states of nature are
equally likely to occur.
 To find an optimal decision:
o For each decision add all the Decision Making Under Risk – EXPECTED
payoffs. VALUE OF PERFECT INFORMATION
o Select the decision with the
 The gain in expected return obtained
largest sum (for profits).
from knowing with certainty the future
state of nature is called:

Decision Analysis: DECISION MAKING UNDER

RISK

 The probability estimate for the

occurrence of each state of nature (if
abailable) can be incorporated in the
search for the optimal decision.
 For each decision calculate its expected
payoff.

Decision Making Under Risk- THE EXPECTED

VALUE CRITERION

Decision Analysis: DECISION TREES

Decision Trees

 The Payoff Table approach is useful for

anon-sequential or single stage.
 Many real-world decision problems
consists of a sequence of dependent
decisions.
 Decision Trees are useful in analyzing
multi-stage decision processes.
Decision Analysis: TYPES OF DECISION MAKERS

Three types of Decision Makers

 Risk Averse - Prefers a certain outcome

to a chance outcome having the same
expected value.
 Risk Taking – Prefers a chance outcome
to a certain outcome having the same
expected value.
 Risk Neutral – Is indifferent between a
chance outcome and certain outcome
having the same expected value.