It is a sequence of decisions. The first question is that, should we conduct a survey or not?

Because of the cost of

$10,000.
ACC-104: MANAGEMENT SCIENCE

LESSON 6: With a sequence of decisions, decision table is not enough as it only has one set of decision. But a decision tree can
handle several decision one after the other.
2ND SEMESTER | A.Y. 202Y – 202Y
LECTURER: MS./SIR

DECISION TREE — Do not build doesn’t have any state-of-nature since

we are already expecting to receive $0 at any cases.
Example: — You did not join the market for storage sets so even
if the market turned out good or bad, it is not going
Mr. Thompson is thinking if he should build a large, small,
to affect you.
or do not build a plant that include storage sheds.

Alternatives Favorable Market Unfavorable Market

Large Plant $200,000 - $180,000
EMV (1) = 200,000 (0.5) + (-180,000) (0.5)
Small Plant $100,000 - $20,000
Do Not Build 0 0 = $ 10,000
PROBABILITY 0.5 0.5 EMV (2) = 100,000 (0.5) + (-20,000) (0.5)
= $ 40,000
EMV (L) = 200,000 (0.5) + (-180,000) (0.5)
= $ 10,000 — After moving forward, we move backward.
EMV (S) = 100,000 (0.5) + (-20,000) (0.5) — Forward = decision  state of nature  probabilities
= $ 40,000  payoffs
EMV (DB) = 0 (0.5) + 0 (0.5) — Backward = EMV  state of nature  decision
=$0 — The decision is based on the payoffs as seen in the
end.
— We will choose from our choices ($10,000;
 Decision Tree has two kinds of nodes: $40,000; 0)
o ▢  Decision node — Every time we have a state-of-nature node, it must always come with probability.
o ◯  State-of-nature node — There is a change in probability after the second decision point. Given that the survey results favorable, the
percentage of the favorable market is higher than unfavorable market. While in the survey that results negative,
 When you make a decision tree, it is just a logical the unfavorable market is higher than the favorable market.
arrangement of things. — Conditional Probabilities
 Decision comes first because decision happens first o “What is the probability of the favorable market given that we have favorable survey results”
before a state of nature happens.
P (favorable market | favorable survey results) = 0.78

P (unfavorable market | favorable survey results) = 0.22

o | = given

— The payoff of $200,000 became $190,000 because of the cost of the survey.
— The payoff of -$180,000 became -$190,000 because of the cost of the survey—there is an additional loss of
$10,000.
— When we did not conduct survey, our probability and payoffs should stay the same, as we did not pay for the
survey.

— The decision tree has an advantage over the 2ND EXAMPLE:

decision table.
Bill Holliday is not sure what he should do. He can either build a quadplex (i.e., a building with four apartments), build
a duplex, gather additional information, or simply do nothing. If he gathers additional information, the results could be
either favorable or unfavorable, but it would cost him $3,000 to gather the information. Bill believes that there is a 50-
50 chance that the information will be favorable. If the rental market is favorable, Bill will earn $15,000 with the
quadplex or $5,000 with the duplex. Bill doesn't have the financial resources to do both. With an unfavorable rental
market, however, Bill could lose $20,000 with the quadplex or $10,000 with the duplex. Without gathering additional
1ST EXAMPLE: information, Bill estimates that the probability of a favorable rental market is 0.7. A favorable report from the study
would increase the probability of a favorable rental market to 0.9. Furthermore, an unfavorable report from the
There is a sale of storage sheds has increased by 20%. When we hear that words, we first conduct market research additional information would decrease the probability of a favorable rental market to 0.4. Of course, Bill could forget all
because it might work in US but not in the Philippines. of these numbers and do nothing. What is your advice to Bill?
The cost of the survey is $10,000.

APRIL KAE APRIL KAE APRIL KAE APRIL KAE APRIL KAE APRIL KAE
2|Page
 4th EXAMPLE:

A financial advisor has recommended two possible mutual

funds for investment: Fund A and Fund B. The return that
will be achieved by each of these depends on whether the
economy is good, fair, or poor. A payoff table has been
constructed to illustrate this situation:

Investment Good Economy Fair Economy Poor Economy

(0.2) (0.3) (0.5)
Fund A $10,000 $2,000 -$5,000
Fund B $6,000 $4,000 0

EMV (1) = 8,500 (0.50) + (-3,000) (0.50)

= $ 2,750
EMV (2) = 12,000 (0.9) + (-23,000) (0.1)
= $ 8,500
EMV (3) = 2,000 (0.9) + (-13,000) (0.1)
= $ 500
EMV (4) = 12,000 (0.4) + (-23,000) (0.6)
= – $ 9,000
EMV (5) = 2,000 (0.4) + (-13,000) (0.6) EMV (1) = 10,000 (0.2) + 2,000 (0.3) + (-5,000) (0.5)
= – $ 7,000 = $ 100
EMV (6) = 15,000 (0.7) + (-20,000) (0.3) EMV (2) = 6,000 (0.2) + 4,000 (0.3) + 0 (0.5)
= $ 4,500 = $ 2,400
EMV (7) = 5,000 (0.7) + (-10,000) (0.3)
= $ 500
CONCLUSION: You should choose Fund B to have an
average return of $2,400.
— The probability of a favorable market given that there is no study conducted is 0.7.
— The probability of a favorable market given that there is a study that gives favorable results is 0.9.
— Even if the results of the study are favorable, we still choose to “do nothing” because there is still a small possibility
that it will be unfavorable—it is just a survey and the probability was only 50%.
— “-$3,000” because you did not do duplex or quadplex, but we spend something on the survey.

CONCLUSION: Billy Holidays should not gather additional information and build Quadplex to earn $4,500 on the average.

3rd EXAMPLE:

A group of medical professionals is considering the

construction of a private clinic. If the medical demand is
high (i.e., there is a favorable market for the clinic), the
physicians could realize a net profit of $100,000. If the
market is not favorable, they could lose $40,000. Of
course, they don't have to proceed at all, in which case EMV (1) = 100,000 (0.5) + (-40,000) (0.5)
there is no cost. In the absence of any market data, the = $ 30,000
best the physicians can guess is that there is a 50-50
chance the clinic will be successful.
CONCLUSION: The medical professionals should
Construct a decision tree to help analyze this problem. construct a private clinic to have an average net income
What should the medical professionals do? of $30,000.

APRIL KAE APRIL KAE APRIL KAE APRIL KAE APRIL KAE APRIL KAE
3|Page 4|Page