Unit 3.

DECISION TREE ANALYSIS

Decision Theory is an analytic and systematic approach to the study of decision- making. It uses
mathematical models useful in helping managers make the best possible decisions.

Steps in Decision-Making:
1. Clearly define the problem at hand;
2. List possible alternatives;
3. Identify the possible outcomes or states of nature;
4. List the payoff (typically profit) of each combination alternatives and outcomes;
5. Select one of the mathematical decision theory models; and
6. Apply the model and make decision.

Types of Decision-Making Environment:

 Decision making under certainty
 Decision making under uncertainty
 Decision making under risk

 DECISION MAKING UNDER CERTAINTY - decision makers know with certainty on the consequence
of every alternative or decision, choosing the alternative that will maximize their well-being or will
result in the best outcome.

 DECISION MAKING UNDER UNCERTAINTY – from the several possible outcomes for each alternative,
decision maker does not know the probabilities of the various outcome.

 DECISION MAKING UNDER RISK – a decision situation in which several possible states of nature may
occur, and the probabilities of these states of nature are known; and one of the most popular methods
of making decisions under risk is selecting the alternative with the highest monetary expected
value.

3.1 Mathematical Expectation (ME) or Expected Value (EV)

Mathematical expectation or expected value will make use the concept of probability (P).

Probability values range from 0 to 1 or 0% to 100%.

Formula:
EV = PX , where: EV = expected value
P = Probability value
X = represent the amount
of money

1
If an event has several possible outcome with probability P1, P2, P3,…Pn and X denotes a variable and
can assume the values X1, X2, X3,… Xn, then
EV = P1(X1) + P2(X2) + P2(X3) + … + Pn(Xn)

If the expected value is negative, it indicates a lose instead of a gain.

Example 6.
A fair coin is tossed. If the coin lands tail Mr. X will receive ₱ 20, and pay ₱15 if it lands
head. Find the EV.

Solution: Since there are only two possible outcomes, head or tail,
P(tail)= ½ and P(head)= ½ ,
So, if P1 = tails, P2 = heads, and X1 = 20 , X2 = 15 ;
EV = P1(X1) + P2(X2) = ½ (20) + ½ (-15) = 10 - 7.5 = ₱2.50

This means that the game is fair for Mr. X.

Example 7.
The operations manager of a construction firm has to decide whether to accept a bid or
not. If he accepts the bid, the firm may gain ₱ 2.5 million if it succeeds, or lose 1.5 million
if it fails. The probability that it will succeed is 35%. Find the expected value if the firm
accepts the bid.

Solution: P1=35% = 0.35 , X1 = 2.5M ; P2 = 65%= 0.65 , X2 = -1.5M

EV = (0.35)(2.5) + (0.65)(-1.5) = 0.875 + (-0.975)
EV = - 0.1 This means that the firm is expected to lose

2
 3.2 DECISION TREE

A decision tree is a schematic model of alternative available to the decision maker, along with their
possible consequences. It is composed of a number of NODES that have branches casting from it.

Two types of nodes that are used in a decision tree:

a square which represents a decision point; and

a circle which represents for a chance event, usually the EV is

written inside the circle.

NOTES:
o The branches of the decision tree having square nodes represent alternatives and branches with
circular nodes represent chance events or uncertainty external events.
o After drawing the decision tree, analysed it from right to left, that is from the last decision that
might be made.
o For each decision, choose the alternative that will yield the largest return or the least cost.

Sample of a decision tree:

The diagram on the left shows
the most basic elements that make
up a decision tree:

First, the square nodes represent

decisions to be made. These are the
decisions that you can make with
certainty. The square labeled with 1
here is a decision. The branches
coming out of square 1 lead to the
different options that you have as a
result of making decision 1.

Circles A and B are options, and

the circles around them represent
uncertainty as to what outcomes
might happen. Unlike the squares,
which have certainty, these circles
represent external events that you
have no control over.

3
Each path you take, from left to right, leads to a different outcome. In this case, there are 7 different
outcomes with expected values calculated by the user to help understand the process. Once your
decision tree is completely made and drawn out, quantitative numbers associated with those
outcomes can help you decide which decision is best for you.

Note: Quantitative numbers are the associated probabilities.

4
 Example 8.

The Manager of a corporation has to decide whether to prepare a bid or not. It costs ₱
10,000 to prepare the bid. If the bid is submitted, the probability that the contract will be
awarded is 65% and the company will earn an income of ₱ 65,000 if it succeeds or pay
₱25,000 if it fails. The probability of success is 70%. Is it advisable to prepare the bid?
Solution:

At the end of the success branch, ₱65,000 is the

return, but since there is a cost of ₱10,000 for bid
preparation, then ₱10,000 should be subtracted.

Since a fine of ₱25,000 is forced in case of failure, and

there is also a cost of ₱10,000 for bid preparation,
– 25,000 – 10,000 are indicated at the end of the
failure branch.

5
 Example 9.

You went to the racetrack choosing between 2 horses: Jaguar and George.

Someone came and offered you a gambler’s anti-insurance. If you agree to it, they
pay you ₱200 up front. You agreed to pay them 50% of any winnings (that is, ₱100 if Jaguar
wins, and ₱500 if George wins).

You can bet on Jaguar. It costs ₱100 to place a bet; you will be paid ₱200 if he wins (or a net
profit of ₱100).

You can bet on George. It costs ₱100 to place a bet; you will be paid ₱1100 if he wins (for a
net profit of ₱1000).

You believe that Jaguar has a probability 0.7 of winning and that George has a probability
0.1 of winning.

Would you take the insurance or not? To whom you are going to bet, Jaguar or George?

SOLUTION:
a. There are 2 decision points, take the insurance or not and bet on Jaguar or George.

2
Jaguar
1 Take the
insurance George

3
Don’t take
the insurance
Jaguar

George

b. The chances of winning upon betting on Jaguar or George:

4
Lose(0.3
)
win(.7
)
5 Lose(0.9)

5
Win (0.1)
6 Lose (0.3)

7 Win(0.7)

Lose (0.9)

Win (0.1)

6
 AS A TEST TO YOURSELF, COMPLETE THE SOLUTION OF Example 9.
“Can you indicate now the amount at the end of the arrows of chance events?”
“Write the expected values (EVs) in each nodes, circular and squares, starting from the right going to
the left, in order to have the complete entries of the tree diagram.”
“Formulate your decision.”

Readings: For additional inputs on decision tree analysis, click on this link:
https://theinvestorsbook.com/decision-tree-analysis.html

TEST YOURSELF 3.0

USING THE DECISION TREE MODEL, FORMULATE A DECISION FOR THE

FOLLOWING PROBLEM. Compare your answer with solutions in the appendices:

• A man has to decide whether to resign or not from his present position and apply for a job
offering him twice his present monthly salary, that is if he passes the qualifying test. At present
he receives ₱10,000 monthly compensation. The offer in another company has a condition that
he will not be allowed to take the qualifying test unless he resigns from his present post. If he
passes the qualifying test he will be immediately be taken in and have a monthly pay of ₱20,000.
If he fails, he will remain jobless. He feels that his chance of passing the test is 45%. Suppose he
decides to base his decision on expected value, should he resign from his present post or not?

7
 UNIT SUMMARY

Decision Theory is an analytic and systematic approach to the study of decision- making. It
uses mathematical models useful in helping managers make the best possible decisions.

A decision tree is a schematic model of alternative available to the decision maker, along
with their possible consequences. It is composed of a number of NODES that have branches
casting from it.

Two types of nodes that are used in a decision tree:

 A square which represents a decision point; and

 a circle which represents for a chance event, usually the EV is

written inside the circle.

Notes:
o The branches of the decision tree having square nodes represent alternatives and
branches with circular nodes represent chance events or uncertainty external events.
o After drawing the decision tree, analysed it from right to left, that is from the last decision
that might be made.
o For each decision, choose the alternative that will yield the largest return or the least
cost.

8
ANSWER KEY to the TEST YOURSELF ITEMS:

TEST YOURSELF 3.0

Pass the Q. test
20,000
P=0.45
resign 900
0 Fail the Q.
test 0
P=0.55
10,000 not resign ₱10,00
0

EV = 20,000(0.45) + 0 ().55) = 9000

DECISION: HE SHOULD NOT RESIGN.