Session - Decision-making under Uncertainty and Risk

Exercise #1
The success of a project to build a new product depends on the
performance features of the product.
The development effort for this new product can be directed in any of
three possible directions: strategies A, B & C, each of which will result in a
product with different performance features.
One of the following three future states of nature will exist when the
product development effort ends:
N1 represents no competing products in the market,
N2 represents a competing product that may come anytime between 0-
6 months, and
N3 represents a competing product in the market.
2
 Back

Exercise #1…

The payoff table given below gives the likely profits in lakhs of rupees.

State of nature

Strategy N1 N2 N3

A 60 30 -20

B 60 50 60
C 90 70 40

Which strategy should be followed?

3
Decision making under risk
• When there are several possible states of nature and the probabilities
associated with each possible state are known

 The most popular method – choose the alternative with the highest
Expected Monetary Value (EMV)

𝐸𝑀𝑉 𝐴𝑖 = ෍ 𝑋𝑖𝑗 𝑃(𝑋𝑖𝑗 )

𝑗

where
𝑋𝑖𝑗 = Payoff for the alternative 𝑖 𝐴𝑖 in state of nature 𝑗
𝑃(𝑋𝑖𝑗 ) = Probability of achieving payoff 𝑋𝑖𝑗 (i.e., probability of the state of nature 𝑖)
∑ = summation symbol
4
EMV for Thompson Lumber

State of nature

Favorable market Unfavorable market

Alternative ($) ($)
Construct a large plant 200,000 –180,000

Construct a small plant 100,000 –20,000

Do nothing 0 0

• Favorable market has a probability of occurrence of 0.90.

• Which alternative would give the highest EMV?
5
EMV for Thompson Lumber…

State of nature

Favorable Unfavorable
Alternative market ($) market ($) EMV ($)

Construct a large plant 200,000 –180,000 162,000

Best EMV
Construct a small plant 100,000 –20,000 88,000

Do nothing 0 0 0

Probabilities 0.90 0.10

6
 Sensitivity analysis
Define P = probability of a favorable market

[2] EMV(small plant)

= ($100,000 * P) − ($20,000 * (1 − P))
[1] EMV(large plant) = $100,000P − $20,000 + $20,000P
= ($200,000 * P) − ($180,000 * (1 − P)) = $120,000P − $20,000
= $200,000P − $180,000 + $180,000P
= $380,000P − $180,000 [3] EMV(do nothing)
= ($0 * P) + ($0 * (1 − P)
= $0
7
Sensitivity analysis…
EMV Values

300,000

200,000 EMV (large plant)

Point 2

100,000 EMV (small plant)

Point 1

0 EMV (do nothing)

.167 .615 1
–100,000
Values of P
–200,000
Best alternative Range of P values
Do nothing Less than 0.167
Construct a small plant 0.167 − 0.615
Construct a large plant Greater than 0.615 8
More information...

• Scientific Marketing, Inc. offers an analysis that will provide certainty

about market conditions (favorable).

• Additional information will cost $ 65,000.

• Should Thompson Lumber purchase the information?

9
EVPI and EVwPI
• EVPI (Expected Value of Perfect Information) places an upper bound
on what you should pay for additional information.

• EVwPI (Expected Value with Perfect Information) is the long-run

average return/payoff if we have perfect information before a
decision is made.

EVwPI = ∑ (best payoff in state of nature i) *

(probability of state of nature i)

EVPI = EVwPI − Best EMV

10
EVPI for Thompson Lumber
State of nature

Favorable Unfavorable
Alternative market ($) market ($) EMV ($)

Construct a large plant 200,000 –180,000 162,000

Best EMV
Construct a small plant 100,000 –20,000 88,000

Do nothing 0 0 0

With perfect information 200,000 0 180,000

EVwPI
Probabilities 0.90 0.10

So, the maximum Thompson Lumber should pay for this perfect information is $ 18,000.
11
Alternative approach: EOL

• EOL (Expected Opportunity Loss) is the cost of not picking the best
solution.

• Steps:
1. Construct an opportunity loss table.
2. For each alternative, multiply the opportunity loss by the probability of that
loss for each possible outcome and add these together.
3. Minimum EOL will always result in the same decision as maximum EMV.
4. Minimum EOL will always equal EVPI.

12
 Alternative approach: EOL…
State of nature
Favorable market Unfavorable market
Alternative ($) ($) EMV ($)

Payoff table Construct a large plant 200,000 –180,000 162,000

Construct a small plant 100,000 –20,000 88,000
Do nothing 0 0 0
Probabilities 0.90 0.10

State of nature
Favorable market Unfavorable market
Alternative ($) ($) EOL ($)
Opportunity Construct a large plant 0 180,000 18,000
loss table
Construct a small plant 100,000 20,000 92,000
Do nothing 200,000 0 180,000
Probabilities 0.90 0.10
13
Why?

To Prove:
Minimum EOL will always result in the same decision as maximum EMV.

To Prove:
Minimum EOL will always equal EVPI.

14
Decision trees
• Any problem that can be presented in a decision table can be
graphically represented in a decision tree.

• Most beneficial when a sequence of decisions must be made

• Components:
 decision points/nodes
 state-of-nature points/nodes

• Decision nodes: one of several alternatives may be chosen

• State-of-nature nodes: one state of nature will occur

15
Structure of decision trees

• Trees start from left to right

• Trees represent decisions and outcomes in sequential order
• Squares represent decision nodes
• Circles represent states of nature nodes
• Lines or branches connect the decisions nodes and the states of nature

16
Steps of decision tree analysis

1. Define the problem

2. Structure or draw the decision tree

3. Assign probabilities to the states of nature

4. Estimate payoffs for each possible combination of alternatives and

states of nature

5. Solve the problem by computing expected monetary values (EMVs)

for each state-of-nature node
17
 Thompson Lumber’s decision tree
A State-of-Nature Node
Favorable market
A Decision Node
1
Unfavorable market

Favorable market
Construct
2
small plant Unfavorable market

18
 Exercise #4

Thompson Lumber’s decision tree

EMV = 162,000
Payoffs
Favorable market (0.9)
200,000
Alternative with best 1
EMV is selected Unfavorable market (0.1)
–180,000

Favorable market (0.9)

100,000
Construct
2
small plant Unfavorable market (0.1)
–20,000

EMV = 88,000

19
 Thank you!

Questions/Comments?

20