KATHLEEN LAICA P.

SABLAY BSA2B

ACTIVITY #5
MANAGEMENT SCIENCE
UNIT 5 – DECISION ANALYSIS

Problem statement:

Bank of Kaperahan (BOK), a prestigious bank in the Philippines, is contemplating its

future plans on whether to:

a. expand
b. maintain status quo
c. merge with other banks

If one of the first two alternatives is chosen, the bank will still merge with other bank
at the end of a year. The amount of profit that could be earned by merging in a year
depends on market conditions, including the status of the economy.

STATE OF NATURE

DECISION GOOD MARKET & BAD MARKET &

ECONOMIC CONDITION ECONOMIC CONDITION
EXPAND 40,000,000 25,000,000
MAINTAIN STATUS QUO 68,000,000 -8,000,000
MERGE 16,000,000 16,000,000
The following payoff table describes this decision situation:

A. Determine the best decision by using the following decision criteria:

1. Maximax
STATE OF NATURE
DECISION GOOD MARKET & BAD MARKET &
ECONOMIC CONDITION ECONOMIC CONDITION
EXPAND 40,000,000 25,000,000
MAINTAIN STATUS QUO 68,000,000 -8,000,000
MERGE 16,000,000 16,000,000

In Maximax Criterion the decision-maker chose 68,000,000 and ignores the possible
loss of -8,000,000. Because those who use the Maximax criterion assume a very
optimistic future with respect to the state of nature.
 2. Maximin
STATE OF NATURE
DECISION GOOD MARKET & BAD MARKET &
ECONOMIC CONDITION ECONOMIC CONDITION
EXPAND 40,000,000 25,000,000
MAINTAIN STATUS QUO 68,000,000 -8,000,000
MERGE 16,000,000 16,000,000

The minimum payoff of this is 25,000,000, -8,000,000 and 16,000,000. The

maximum of these payoffs is 25,000,000. Because the alternatives studied only
include the worst possible outcomes, this decision is considered to be conservative.

3. Minimax regret

GOOD MARKET & ECONOMIC BAD MARKET & ECONOMIC

CONDITION CONDITION
68,000,000 - 40,000,000 = 28,000,000 25,000,000 - 25,000,000 = 0

68,000,000 - 68,000,000 = 0 25,000,000 + 8,000,000 = 33,000,000

68,000,000 - 16,000,000 = 52,000,000 25,000,000 - 16,000,000 = 9,000,000

REGRET TABLE
STATE OF NATURE

DECISION GOOD MARKET & BAD MARKET &

ECONOMIC CONDITION ECONOMIC CONDITION
EXPAND 28,000,000 0
MAINTAIN STATUS QUO 0 33,000,000

MERGE 52,000,000 9,000,000

According to the Minimax Regret Criterion, the decision was to expand the Bank of
Kaperahan (BOK). This particular decision is based on the philosophy that the Bank
of Kaperahan will experience the least amount of regret by expanding the said bank.
In other words, if the BOK choose to maintain status quo, the regret will be
33,000,000. if they choose to merge, 52,000,000 worth of regret could result;
however, if they choose to expand the result of regret will be 28,000,000.

4. Hurwicz (α = 0.25)
DECISION VALUES

EXPAND 40,000,000(0.25) + 25,000,000(0.75) = 28,750,000

MAINTAIN STATUS QUO 68,000,000(0.25) – 8,000,000 (0.75) = 11,000,000

MERGE 16,000,000(0.25) + 16,000,000(0.75) = 16,000,000

The Hurwicz criterion specifies the selection of the decision alternative corresponding
to the maximum weighted value, which is 28,750,000. Thus, the decision would be to
expand.

5. Equal likelihood

DECISION VALUES

EXPAND 40,000,000(0.50) + 25,000,000(0.50) = 32,500,000

MAINTAIN STATUS QUO 68,000,000(0.50) – 8,000,000 (0.50) = 30,000,000

MERGE 16,000,000(0.50) + 16,000,000(0.50) = 16,000,000

32,500,000 is the highest weighted value, Bank of Kaperahan’s decision would be to

Expand.

SUMMARY OF CRITERIA RESULTS

CRITERION DECISION
MAXIMAX MAINTAIN STATUS QUO
MAXIMIN EXPAND
MINIMAX REGRET EXPAND
HURWICZ EXPAND
EQUAL LIKELIHOOD EXPAND

The decision to Expand was designated most often by the various decision criteria.
Notice that the decision to merge was never indicated by any criterion. It is because
the payoffs for expand, under either set of future economic conditions, are always
better than the payoffs to merge. In fact, the merge decision alternative could have
been eliminated from consideration under each of our criteria.

B. Assume that it is now possible to estimate a probability of 0.80 that good

market and economic conditions will exist and a probability of 0.20 that poor
conditions will exist. Determine the best decision by using expected value and
expected opportunity loss.
 STATE OF NATURE

DECISION GOOD MARKET & BAD MARKET &

ECONOMIC CONDITION ECONOMIC CONDITION
(0.80) (0.20)
EXPAND 40,000,000 25,000,000
MAINTAIN STATUS QUO 68,000,000 -8,000,000
MERGE 16,000,000 16,000,000

The expected value (EV) for each decision is computed as follows:

DECISION VALUES

EXPAND 40,000,000(0.80) + 25,000,000(0.20) = 37,000,000

MAINTAIN STATUS QUO 68,000,000(0.80) – 8,000,000 (0.20) = 52,800,000

MERGE 16,000,000(0.80) + 16,000,000(0.20) = 16,000,000

The best decision is the one with the greatest expected value and because the greatest
expected value is 52,800,000, the best decision is to maintain the status quo. The
expected value means that if this decision situation occurred a large number of times,
an average payoff of 52,800,000 would result.

The expected opportunity loss (EOL) for each decision is computed as follows:
DECISION VALUES

EXPAND 28,000,000 (0.80) + 0 (0.20) = 22,400,000

MAINTAIN STATUS QUO 0 (0.80) + 33,000,000 (0.20) = 6,600,000

MERGE 52,000,000 (0.80) + 9,000,000 (0.20) = 43,400,000

As with the minimax regret criterion, the best decision results from minimizing the
regret or in this case, minimizing the expected regret or opportunity loss. Because
6,600,000 is the minimum expected regret, the decision is to maintain status quo.

C. Compute the expected value of perfect information

Expected Value of Perfect Information

STATE OF NATURE

DECISION GOOD MARKET & BAD MARKET &

ECONOMIC CONDITION ECONOMIC CONDITION
 (0.80) (0.20)
EXPAND 40,000,000 25,000,000
MAINTAIN STATUS QUO 68,000,000 -8,000,000
MERGE 16,000,000 16,000,000

Thus, each of the decision outcomes obtained using perfect information must be
weighted by its respective probability:

68,000,000 (0.80) + 25,000,000 (0.20) = 59,400,000

The amount 59,400,000 is the expected value of the decision, given perfect
information, not the expected value of perfect information. The expected value of
perfect information is the maximum amount that would be paid to gain information
that would result in a decision better than the one made without perfect information.
Recall that the expected value decision without perfect information was to expand,
and the expected value was computed as:

40,000,000(0.80) + 25,000,000(0.20) = 37,000,000

The expected value of perfect information is computed by subtracting the expected

value without perfect information 37,000,000 from the expected value given perfect
information 59,400,000

EVPI = 59,400,000 – 37,000,000 = 22,400,000

The expected value of perfect information, 22,400,000 is the maximum amount.

D. Develop a decision tree, with expected values at the probability nodes

40,000,000
EXPAND
25,000,000

MAINTAIN STATUS 68,000,000

QUO

MERGE -8,000,000

16,000,000

16,000,000