Ch-5 Decision Making

Chapter Five:
Decision Theory
2.1. Decision Making Under Condition of Uncertainty
 Under complete uncertainty, either no estimates of the
probabilities for the occurrence of the different states of nature
are available.
 Under this circumstance, the decision maker lacks confidence in
the state of nature to make decision.
 For this kind of decision, probabilities are not used at the choice
of the best alternative.
 Most of the rules for decision making under uncertainty express a
different degree of decision maker´s optimism.
 For making decisions under uncertainty condition, different
techniques to be used. Some of these are as follows:
2.1.1. The Maximax Criterion

 The maximax criteria is appropriate for extreme optimists that
expect the most favorable situation.
 Decision makers choose the alternative that could result in the
maximum payoff.
 Under this criteria, the decision maker will find the largest payoff
in the decision matrix and select the alternative associated with it.
 The largest payoff is determined for each alternative and then the
largest payoff from these values (maximax) is selected.
o The procedure for maximax is shown in the following table:
Example 1:
Demand® Low Moderate High Row
Order Maximum
Small 50 50 50 50
Medium 42 52 52 52
Large 34 44 54 54 ¬
Maximum
 The best overall profit is $54 in the third row. Hence, the
maximax rule leads to the large order (the grocer hopes that the
demand will be high).
2.1.2. The Wald Criteria (Maximin Rule)
 The maximin rule (Wald criterion) represents a pessimistic
approach when the worst decision results are expected.
 The decision maker determines the smallest payoff for each
alternative and then chooses the alternative that has the best
(maximum) of the worst (minimum) payoffs .
Example 2:
Demand Low Moderate High Row

Order Minimum
Small 50 50 50 50 Maximum
Medium 42 52 52 42
Large
Since 50 is the 34
largest, the44low order should
54 be chosen
34 (if order is low, the
$50 grocer‘s profit is guaranteed).
2.1.3. The Hurwicz Criterion
 The Hurwicz - criterion represents a compromise between the
optimistic and the pessimistic approach to decision making
under uncertainty.
 The measure of optimism and pessimism is expressed by an
optimism - pessimism index ( ), 0 <= <=1.
 The more this index is near to 1, the more the decision maker is
optimistic.
 If  = 0, the decision maker is said to be completely pessimistic.
 By means of the index , if  is the coefficient of optimism, 1- 
is the coefficient of pessimism.
 The weighted average will be computed for each alternative and
the alternative with the largest weighted average should be
chosen.
 If we choose = 0.7 at determining the best size of the order in
examples 1 &2 above, the weighted average (WA) of the largest
and the smallest profit for each size of the order has the
following values:
 WA (small) = 0.7* 50 + 0.3 * 50 = 50
 WA (medium) = 0.7* 52 + 0.3 * 42 = 49
 WA (large) = 0.7* 54 + 0.3 *34 = 48
 Maximizing the weighted average of the largest and the smallest

profit, the small order should be selected.
2.1.4. The savage criterion (Minimax Regret Rule)
 The maximax and maximin rules and the Hurwicz criterion
can be criticized because they focus only on extreme payoffs
and exclude the other payoffs.
 An approach that does take all payoffs into account is the

minimax regret rule (Savage criterion).
 This rule represents a pessimistic approach used for an
opportunity loss table.
 The opportunity loss reflects the difference between each
payoff and the best possible payoff in a column.
 The opportunity loss can be defined as the amount of profit
foregone by not choosing the best alternative for each state of
nature.
 The opportunity loss amounts are found by identifying the greatest
payoff in a column and, then, subtracting each of the other values
in the column from that payoff.
 The values in an opportunity loss table can be viewed as potential

”regrets” that might be suffered as the result of choosing various
alternatives.
 Minimizing the maximum possible regret requires identifying the

maximum opportunity loss in each row and, then, choosing the
alternative that would yield the minimum of those regrets (this
alternative has the “best worst”).
 To illustrate the Savage criterion procedure, we will recall the
decision problem given in example 1 &2 and first construct the
corresponding regret table.
 Payoff table:
Demand ® Low Moderate High
Order
Small 50 50 50
Medium 42 52 52
Large 34 44 54
 In the first column of the payoff matrix, the largest number is 50, so each of
the three numbers in that column must be subtracted from 50.
 In the second column, we must subtract each payoff from 52 and in the third
column from 54 as calculations are summarized in the following Table. A
column with the maximum loss in each row is presented to this table.
Demand® Low Moderate High Maximum

Loss
Order
Small 0 2 4 4 ¬ Minimum
Medium 8 0 2 8
Large 16 8 0 16
 To minimize the maximum loss, the small order should be chosen.

2.1.5 The Lap place criterion (Equal Likelihood Criterion)
 The lap place criterion assumes that all states of nature are
equally likely.
 Under this assumption, the decision maker can compute the

average payoff for each row (the sum of the possible
consequences of each alternative is divided by the number of
states of nature).
 Finally, the alternative that has the highest row average will be
selected as best alternative. This procedure is illustrated by the
following calculations with the data
 The procedure for the Lap Place Criterion (Equal Likelihood
Criterion) is illustrated by the following calculations with the
data given under example 1 and 2.
 Expected monetary value (EMV):

 EMV (small) = (50 + 50 + 50)/3 = 50
 EMV (medium) = (42 + 52 + 52)/3 = 48.7
 EMV (large) = (34 + 44 + 54)/3 = 44
 Since the profits at the small order have the highest average, that
order should be realized.
2.2 Decision Making Under Condition of Risk
 In this case, the decision maker doesn´t know which state of

nature will occur but can estimate the probability of occurrence
for each state.
 The probabilities may be subjective (they usually represent
estimates from experts in a particular field), or they may reflect
historical frequencies.
 A widely used approach to decision making under risk is

expected monetary value criterion.
 There are also other techniques that can be used to make

decision under this condition.
2.2.1. Expected Monetary Value Criterion
 The Expected Monetary Value (EMV) of an alternative is

calculated by multiplying each payoff that the alternative can
yield by the probability for the relevant state of nature and
summing the products.
 The value is computed for each alternative, and the one with the
highest EMV is selected.
 Suppose that the grocer can assign probabilities of low,
moderate and high demand on the basis of his experience with
sale of pastry.
 The estimates of these probabilities are 0.3, 0.5, 0.2,
respectively.
 We will recall the payoff table for the considered problem.
 Payoff table:
Demand Low Moderate High

Order
Small 50 50 50
Medium 42 52 52
Large 34 44 54
 The EMV for various sizes of the order are as follows:
 EMV (small) = 0.3*50 + 0.5*50 + 0.2*50 = 50

 EMV (medium) = 0.3*42 + 0.5*52 + 0.2*52 = 49
 EMV (large) = 0.3*34 + 0.5*44 + 0.2*54 = 43
 Therefore, in accordance with the EMV criterion, the small
order should be chosen.
 Note that the EMV of $50 will not be the profit on any one day.
It represents an expected or average profit.
 If the decision were repeated for many days (with the same
probabilities), the grocer would make an average of $50 per day
by ordering the small amount of pastry.
 Even if the decision were not repeated, the action with the
highest EMV is the best alternative that the decision maker has
available.
 The EMV criterion remains as the most useful of all the
decision criteria for decision making under risk.
 For risky decisions, a sensible approach is first to calculate the

EMV, and then to make a subjective adjustment for the risk in
making the choice.
2.2.2. The Expected Opportunity Loss (EOL)
Criterion
 The expected opportunity loss (EOL) is nearly identical to the
EMV approach, except that a table (or matrix) of opportunity
losses (or regrets) is used.
 The opportunity losses for each alternative are weighted by the

probabilities of their respective states of nature and these
products are summed.
 The alternative with the smallest expected loss is selected as the

best choice.
 We will use EOL procedure in the regret matrix shown
above
Regret table:
Demand® Low Moderate High
Order
Small 0 2 4
Medium 8 0 2
Large 16 8 0
 Supposing that the probabilities of various sizes of the demand
are 0.3, 0.5, 0.2, we can determine the EOL for each size of the
order as follows:
 EOL (small) = 0.3*0 + 0.5*2 + 0.2*4 = 1.8
 EOL (medium) = 0.3*8 + 0.5*0 + 0.2*2 = 2.8
 EOL (large) = 0.3*16 + 0.5*8 + 0.2*0 = 8.8
 Since the small order is connected with the smallest EOL, it is
the best alternative.
 The EOL approach resulted in the same alternative as the EMV

approach.
 The two methods always result in the same choice, because

maximizing the payoffs is equivalent to minimizing the
opportunity losses.

Ch-5 Decision Making

Uploaded by

Copyright:

Available Formats

Ch-5 Decision Making

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Ch-5 Decision Making

Uploaded by

Copyright:

Available Formats

Chapter Five:

2.1.1. The Maximax Criterion

Demand Low Moderate High Row

 Maximizing the weighted average of the largest and the smallest

 An approach that does take all payoffs into account is the

 The values in an opportunity loss table can be viewed as potential

 Minimizing the maximum possible regret requires identifying the

Demand ® Low Moderate High

Demand® Low Moderate High Maximum

 To minimize the maximum loss, the small order should be chosen.

 Under this assumption, the decision maker can compute the

 Expected monetary value (EMV):

 In this case, the decision maker doesn´t know which state of

 A widely used approach to decision making under risk is

 There are also other techniques that can be used to make

 The Expected Monetary Value (EMV) of an alternative is

Demand Low Moderate High

 EMV (small) = 0.3*50 + 0.5*50 + 0.2*50 = 50

 For risky decisions, a sensible approach is first to calculate the

 The opportunity losses for each alternative are weighted by the

 The alternative with the smallest expected loss is selected as the

 The EOL approach resulted in the same alternative as the EMV

 The two methods always result in the same choice, because

You might also like

 EMV (small) = 0.350 + 0.550 + 0.2*50 = 50