Decision making theory

Presented by –
Ananta Dutta (17MS06001)
Rohit Anand (17MS06005)
 Introduction
Decision theory deals with methods for determining the
optimal course of action when a number of alternatives are
available and their consequences cannot be forecast with
certainty.

Very simply, the decision problem is how to select the best of

the available alternatives.
 why decision theory?
 Certainty exists when there is only one outcome for an
event.
 Uncertainty exists when the decision maker is unable to
ascertain or subjectively estimate the probabilities of the
various states of nature.
 Risk exists when the decision maker does not know with
certainty the state of nature, but the probabilities of
various outcomes is known.
 Elements of Decision problem
 Goals to be achieved
 Decision alternatives (actions, acts)
 State of nature (possible events i.e., states, outcomes of a
random process)
 probabilities of these events
 Payoff (Effectiveness associated with specified
combination of a course of action and state of nature)
 Opportunity loss (Incurred due to failure of not
adopting most favorable course of action or strategy)
steps involved in decision making
problem
 Determine the various alternative courses of actions from
which the final decision has to be made.
 Identify the possible outcomes, called the states of nature or
events for the decision problem.
 Construct a pay off table or opportunity loss table.
 The decision maker chooses the criterion which results in
largest pay off or lowest opportunity loss.
decision under uncertainty
There are five criteria on the basis of which rules for
making a decision is formulated –
1. Minimax criterion
2. Maximin criterion
3. Maximax criterion
4. Laplace criterion
5. Hurwicz criterion
 criterion of pessimism
1. Maximin criterion (Best of Worst)–
 Find minimum assured pay off for each alternative
 Choose the maximum of minimum values
2. Minimax criterion (Regret)–
 Determine maximum possible opportunity loss (regret)
for each alternative
Regret = Best payoff – Payoff received
 Choose the alternative minimum of above losses
 criterion of optimism
3. Maximax criterion (Best of Best)–
 Determine maximum possible payoff
 Select
a alterative which corresponds to maximum of
maximum pay off
 Laplace criterion
4. Laplace criterion –
 Assign equal probabilities to each payoff of a strategy.
Probability = 1 / (no. of states of natures)
 Determine the expected pay off value for each
alternative.
 Select
the alternative which corresponds to the
maximum payoff or minimum cost .
 Criterion of realism
5. Hurwicz criterion –
of optimism α
 Coefficient
0<α<1 where 0 signifies total pessimism and 1 total
optimism.
 Decide the coefficient of optimism and the coefficient of
pessimism.
 Determine the maximum as well as minimum pay off for
each alterative.
 Criterion of realism (cont.)
 Then calculate the weighted average using this formula –
H = α*max payoff + (1- α)*min payoff
 Select the alternative with highest value of H.
 example
A farmer wants to decide which of the three crops he
should plant on his 100 Acre farm. The profit from each is
dependent on the rainfall during the growing seasons. The
farmer has categorized the amount of rainfall as high,
medium, low. His estimated profit for each is show in the
table. If the farmer wishes to plant only one crop, decide
which will be his choice using all above criteria.
 example
Rainfall Crop Crop Crop
A B C Payoff table
High 8000 3500 5000
Medium 4500 4500 5000
Regret table
Low 2000 5000 4000
Rainfall Crop Crop Crop
Max payoff 8000 5000 5000 A B C
Min payoff 2000 3500 4000 High 0 4500 3000
1. Minimax - Crop A or C Medium 500 500 0
2. Maximin – Crop C Low 3000 0 1000
3. Maximax – Crop A Max regret 3000 4500 3000
4. Laplace –
Assign equal probabilities i.e. 1/3. The expected pay off is
calculated for each alterative:
E (Crop A)=1/3(8000)+1/3(4500)+1/3(2000)= 4833
E (Crop B)=4333
E (Crop C)=4666
Hence this criterion selects Crop A.
5. Hurwicz –
degree of optimism α = 0.6

H (Crop A)=0.6*(8000)+(1-0.6)*(2000) = 5600

H (Crop B)=4400
H (Crop C)=4600
Hence this criterion also selects Crop A.
 Decision under risk
Decision-making under risk describes a situation in which
each strategy results in more than one outcomes or payoffs
and the manager attaches a probability measure to these
payoffs.
Under conditions of risk a number of decision criteria are
available. These are –
1. Expected monetary value (EMV) criterion
2. Expected opportunity loss (EOL) criterion
 EMV criterion
 For each decision calculate the expected payoff as follows:

Expected payoff = ∑(Probability*Payoff)

 Select the decision with the maximum expected payoff.

example
 eol criterion
 For each decision calculate the expected opportunity loss as
follows:

Expected opportunity loss = ∑(Probability*Opportunity

loss)

 Select the decision with the minimum EOL value.

example