CHRISTIAN SERVICE UNIVERSITY COLLEGE,

KUMASI

DECISION ANALYSIS
CONT’D

LECTURE 7
Contents
Introduction to Decision Analysis
Steps of Decision-making Process

Types of Decision-making Environment

Assignment
 Decision-making under Uncertainty Cont’d

• Example: A manufacturer manufactures a product, of which

the principal ingredient is a chemical X. At the moment, the
manufacturer spends GH¢1,000 per year on supply of X, but
there is a possibility that the price may soon increase to four
times its present figure because of a worldwide shortage of
the chemical. There is another chemical Y, which the
manufacturer could use in conjunction with a third chemical
Z, in order to give the same effect as chemical X.
 Decision-making under Uncertainty Cont’d

• Chemicals Y and Z would together cost the manufacturer GH

¢3,000 per year, but their prices are unlikely to rise. What
action should the manufacturer take? Apply the maximin and
minimax criteria for decision-making and give two sets of
solutions. If the coefficient of optimism is 0.4, then find the
course of action that minimizes the cost.
 Decision-making under Uncertainty Cont’d

• Solution: The data of the problem is summarized in

the following table (negative figures in the table
represent profit).
Decision-making under Uncertainty Cont’d

States of Nature Courses of Action

S1 (use Y and S2(use X)
Z)
N1 (Price of X - 3,000 - 4,000
increases)
N2 (Price of X does not - 3,000 - 1,000
increase)
 Decision-making under Uncertainty
Cont’d
• (a) Maximin Criterion
States of Nature Courses of Action
S1 S2

-3,000 -4,000

-3,000 - 1,000

Column -3,000 - 4,000

(minimum) Maximim
Decision-making under Uncertainty Cont’d

• Maximum of column minima = - 3,000. Hence, the

manufacturer should adopt action S1

• (b) Minimax (or opportunity loss) Criterion

Decision-making under Uncertainty Cont’d

States of Nature Courses of Action

S1 S2
N1 -3,000 – (-3,000) = -3,000 – (-4,000) =
0 1,000
N2 -1,000 – (-3,000) = -1,000 – (-1,000) =
2,000 0
Maximum 2,000 1,000 Minimax
Opportunity
 Decision-making under Uncertainty Cont’d

• The manufacturer should adopt minimum opportunity loss

course of action S2.
• (c) Hurwicz Criterion: Given the coefficient of optimism equal
to 0.4, the coefficient of pessimism will be 1 - 0.4 = 0.6. Then
according to Hurwicz, select course of action that optimizes
(maximum for profit and minimum for cost) the payoff value
• H = α (Best payoff) + (1 - α) (Worst payoff)
• = α (Maximum in column) + (1 - α) (Minimum in column)
 Decision-making under Uncertainty Cont’d
Course of Best Worst H
Action Payoff Payoff
S1 - 3,000 - 3,000 - 3,000

S2 -1,000 -4,000 - 2,800

• Since course of action S2 has the least cost (maximum profit) =

0.4(-1,000) + 0.6(-4,000) = -GH¢2,800, the manufacturer should
adopt this.
 Assignment

The following matrix gives the payoff (in GHc) of different

strategies (alternatives) S1 S2 and S3 against conditions (events)
N1, N2, N3 and N4
 Decision-making under Uncertainty Cont’d

Strategy State of Nature

N1 N2 N3 N4

S1 4,500 -200 7,000 20,000

S2 22,000 6,000 500 100

S3 18,000 16,000 -3,000 2,000
 Decision-making under Uncertainty Cont’d

• Indicate the decision taken under the following approaches:

• (a) Pessimistic or Maximin criterion
• (b) Optimistic or Maximax criterion
• (c) Equal probability
• (d) Minimax regret criterion
• (e) Hurwicz criterion, the degree of optimism is 0.6
 Decision-making Under Risk

• In decision-making under risk, more than one state of nature exists

and the decision-maker has sufficient information to assign
probability values to the likely occurrence of each of these states.
• When one is aware of the probability distribution of the states of
nature, the best decision is to select that course of action which has
the largest expected payoff value.
• The expected (average) payoff of an alternative is the sum of all
possible payoffs of that alternative, weighted by the probabilities of
the occurrence of those payoffs.
 Decision-making Under Risk

• The most widely used criterion for evaluating various courses

of action (alternatives) under risk is the Expected Monetary
Value (EMV).
Expected Monetary Value (EMV)
• The expected monetary value (EMV) for a given course of
action is the weighted sum of possible payoffs for each
alternative.
 Decision-making Under Risk
•
 Decision-making Under Risk
• Steps for calculating EMV:
1. Construct a payoff matrix listing all possible courses of action and
states of nature. Enter the conditional payoff values associated with
each possible combination of course of action and state of nature
along with the probabilities of the occurrence of each state of
nature.
2. Calculate the EMV for each course of action by multiplying the
conditional payoffs by the associated probabilities and adding these
weighted values for each course of action.
 Decision-making Under Risk

3. Select the course of action that yields the optimal EMV.

 Decision-making Under Risk
Example 1: An investor is given the following investment alternatives
and percentage rates of return.
States of Nature (Market Conditions)
Low Medium High
Regular
Shares 7% 10% 12%
Risky Shares
10% 12% 18%
Property
15% 25% 30%
 Decision-making under Uncertainty Cont’d

• Over the past 300 days, 150 days have been medium market
conditions and 60 days have had high market increases. On
the basis of these data, state the optimum investment
strategy for the investment.
 Decision-making under Uncertainty Cont’d

• Solution
• It is clear from the information given that, the probabilities
of low, medium and high market conditions are 90/300 or
0.30,150/300 or 0.50 and 60/300 or 0.20, respectively. The
expected pay-offs for each of the alternatives are shown
below:
 Decision-making under Uncertainty
Cont’d
Market Conditions Probability Strategy
Regular Shares Risky Shares Property

Low 0.30 0.07 x 0.30 0.10 x 0.30 0.15 x 0.30

Medium 0.50 0.10 x 0.50 0.12 x 0.50 0.25 x 0.50
High 0.20 0.12 x 0.20 0.18 x 0.20 0.30 x 0.20
Expected Return 0.095 0.126 0.230
 Decision-making under Uncertainty Cont’d

• Since the expected return of 23 percent is the highest for

property, the investor should invest in this alternative.
 Expected Monetary Value (EMV) Cont’d
• Example 2: A small company has established a niche for itself in
the personal computer market. It specializes in assembling and
selling PC systems for use by family doctor practices throughout
the UK - a market which since the reform initiatives in the
National Health Service has proved particularly lucrative.
• The company is developing a new PC - based system which it
intends to market under its own brand name next year.

E
 Expected Monetary Value (EMV) Cont’d
• At present the company is trying to decide on the manufacturing
and assembly process to be used. One aspect of this relates to the
keyboard that will be used in the system, which will have specially
labelled function keys. The company has decided that it faces
three alternatives;
(1) It can manufacture/assemble the keyboard itself.
(2) It can buy the keyboards from domestic manufacturer.
(3) It can buy the keyboard from a manufacturer in the Far East.
The information is presented in the table below:
E
 Expected Monetary Value (EMV) Cont’d
Pay-off table: Profit contribution ($000) in terms of each
decision/state of nature combination
State of Nature
Decision/Strategy Low Medium High

Manufacture -15 10 55

Buy Abroad 10 30 25
Buy Domestic 5 20 40
 Expected Monetary Value (EMV) Cont’d

• Assume that the company has been able to quantify the

likelihood of each of the states of nature occurring by attaching
a probability of 0.2 to low sales, 0.5 to medium and 0.3 to high
sales. Use the EMV criterion to determine the best alternative
for the company.
 Expected Monetary Value (EMV) Cont’d
• Solution: Strategies
States of Probability Manufacture Buy Buy
Nature Abroad Domestic

Low 0.2 -15 x 0.2 10 x 0.2 5 x 0.2

Medium 0.5 10 x 0.5 30 x 0.5 20 x 0.5
High 0.3 55 x 0.3 25 x 0.3 40 x 0.3
EMV = 18.5 24.5 23.0
 Expected Monetary Value (EMV) Cont’d

• Based on the calculations of the EMV for the three strategies, it

is logical to recommend that the company buys the keyboard
abroad since it has a higher EMV of $24,500.
 Expected Opportunity Loss (EOL)
• An alternative approach to maximizing expected monetary
value (EMV) is to minimize the expected opportunity loss (EOL),
also called expected value of regret.
• The EOL is defined as the difference between the highest profit
(or payoff) of a state of nature and the actual profit obtained by
the particular course of action taken.
• In other words, EOL is the amount of payoff that is lost by not
selecting that course of action which has the greatest payoff
for the state of nature that actually occurs.
 Expected Opportunity Loss (EOL) Cont’d
• The course of action due to which EOL is minimum is
recommended.
• Since EOL is an alternative decision criterion for decision-
making under risk, therefore, the results will always be the
same as those obtained by EMV criterion discussed earlier.
• In view of this, only one of the two methods should be applied
to reach a decision.
STEP 1 STEP2
Experimental outcome
)

Expected Opportunity Loss (EOL) Cont’d

• Mathematically, it is stated as follows.

• EOL (State of nature, Ni)

• where
• opportunity loss due to state of nature, Niand course of action, Sj
• probability of occurrence of state of nature, Ni
STEP 1 STEP2
Experimental outcome
)

Expected Opportunity Loss (EOL) Cont’d

• Steps for calculating EOL.

1. Prepare a conditional profit table for each course of action
and state of nature combination along with the associated
probabilities.
2. For each state of nature calculate the conditional opportunity
loss (COL) values by subtracting each payoff from the
maximum payoff for that outcome.
STEP 1 STEP2
Experimental outcome
)

Expected Opportunity Loss (EOL) Cont’d

3. Calculate the EOL for each course of action by multiplying the

probability of each state of nature with the COL value and then
add the values.
4. Select a course of action for which the EOL value is minimum.
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

• In the decision-making under risk, each state of nature is

associated with the probability of its occurrence.
• However, if the decision-maker can acquire perfect (complete
and accurate) information about the occurrence of various
states of nature, then he would be able to select a course of
action that yields the desired payoff for whatever state of
nature that actually occurs.
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d

• We have seen that the EMV or EOL criterion helps the decision-
maker select a particular course of action that optimizes the
expected payoff, without the need of any additional
information.
• Expected value of perfect information (EVPI) represents the
maximum amount of money the decision-maker has to pay in
order to get this additional information about the occurrence of
various states of nature before a decision has to be made.
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• Mathematically it is stated as:
• EVPI = (Expected profit with perfect information) - (Expected
profit without perfect information)
• Pi max (Pij) – EMV*
• where pij= best payoff when action, Sj is taken in the presence
of state of nature, Ni.
• Pi = probability of state of nature, Ni
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• EMV* = maximum expected monetary value
• Example 3:
• A company needs to increase its production beyond its existing
capacity. It has narrowed down on two alternatives in order to
increase the production capacity: (a) expansion, at a cost of GH
¢8 million, or (b) modernization at a cost of GH¢5 million. Both
approaches would require the same amount of time for
implementation.
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• Management believes that over the required payback
period demand will either be high or moderate.
• Since high demand is considered to be somewhat less likely
than moderate demand the probability of high demand has
been set at 0.35.
• If the demand is high, expansion would gross an estimated
additional GH¢12 million but modernization would only
gross an additional GH¢6 million, due to lower maximum
production capability.
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• On the other hand, if the demand is moderate, the
comparable figure would be GH¢7 million for expansion
and GH¢5 million for modernization.
(a) Calculate the conditional pofit in relation to various
action-and-outcome combinations and states of nature.
(b) If the company wishes to maximize its expected
monetary value (EMV), should it modernize or expand?
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d

(c) Calculate the EVPI.

(d) Construct the conditional opportunity loss table and
also calculate EOL.
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• Solution:
(a) Define the states of nature: High demand and Moderate
demand (over which the company has no control) and courses of
action (company’s possible decisions): Expand and Modernize.
• Since the probability that the demand is high is estimated at
0.35, the probability of moderate demand must be (1 - 0.35) =
0.65.
• The calculations for conditional profit values are shown below:
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
State of Nature Conditional Profit (million GH¢)
(Demand) Due to Course of Action
Expand (S1) Modernize (S2)
High demand (N 1) 12 -8 = 4 6-5=1
Moderate deman d 7 - 8 = - 1 5 - 5 = 0
(N 2 )
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
(b) The payoff table above can be rewritten as follows along with
the given probabilities of nature.
State of Nature Probability Conditional Profit (million
GH¢)

(Demand) Due to Course of Action

Expand (S1) Modernize (S2)
High demand 0.35 4 1
Moderate demand 0.65 -1 0
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
(b) The payoff table above can be rewritten as follows along with
the given probabilities of nature.
State of Nature Probability Course of Action
Expand (S1) Modernize (S2)
High demand 0.35 4 x 0.35 1 x 0.35
Moderate demand 0.65 -1 x 0.65 0 x 0.65
EMV = 0.75 0.35
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• The calculation of EMV for each course of action S 1 and S2 is
given below:
• EMV (S1) = 0.35(4) + 0.65(- 1) = GH¢0.75 million
• EMV (S2) = 0.35(1) + 0.65(0) = GH¢0.35 million. Thus in order
to maximize EMV the company must choose course of action
S1 (expand). The EMV of the optimal course of action is
generally denoted by EMV*. Therefore,
• EMV* = EMV (S1) = GH¢0.75 million
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d

(c) To calculate EVPI, we shall first calculate EPPI.

EPPI is Expected Profit with Perfect Information
• For calculating EPPI, we choose optimal course of action for
each state of nature, multiply its conditional profit by the given
probability to get weighted profit, and then sum these weights
as shown on the next slide:
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
State of Probability Optimal Profit from Optimal Course of
Nature Course Action (GH¢ million)

(Demand) of Action
Conditional Pft. Weighted Pft.
High Dd 0.35 S1 4 4 x 0.35 = 1.40

Mod. Dd 0.65 S2 0 0 x 0.65 = 0

EPPI = 1.40
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• The optimal EMV* is GH¢0.75 million corresponding to the course of
action S1. Then
• EVPI = EPPI – EMV (S1) = 1.40 - 0.75 = GH¢0.65 million.
• This implies that, if the company could get perfect information (or
forecast) of demand (high or moderate), it should consider paying up
to GH¢0.65 million for that information.
• The expected value of perfect information in business helps in getting
an absolute upper bound on the amount that should be spent to get
additional information on which a given decision is to be based.
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• (d) The opportunity loss values are shown below:
State of Nature Probability Conditional Profit Conditional
(Demand) (GH¢million) Opportunity Loss
Due to (GH¢million) Due to
Course of Action Course of Action
S1 S2 S1 S2
High demand (N 1 ) 0.35 4-4 4-1 0 3
Moderate demand (N2) 0.65 0- - 1 0-0 1 0
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• The conditional opportunity loss values may be explained as
follows: If the demand is (N1) high, then the maximum profit
of GH¢4 million would be achieved by selecting course of
action S1.
• Therefore, the selection of S1 would result in zero
opportunity loss, as this is the best decision that can be
made if N1 occurs.
• If course of action S2, was chosen with a payoff of one
million, then this would result in an opportunity loss of
4 - 1 = GH¢3 million.
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• If moderate demand (N2) occurred, then the best course of
action would be S2 with GH¢ zero million profit.
• The opportunity loss would therefore, be associated with the
selection of S2 but if S1 was selected, then the opportunity
loss would be 0 - (- 1) = GH¢1 million.
• This means, the company would have been GH¢1 million
worse off if it had chosen course of action S1.
STEP 1 STEP2
Experimental outcome
)

Expected Value of Perfect Information (EVPI)

Cont’d
• With the given estimates of probabilities associated with
each state of nature, i.e. P(N1) = 0.35, and P(N2) = 0.65, the
expected opportunity losses for the two courses of action
are:
• EOL(S1) = 0.35(0) + 0.65(1) = GH¢ 0.65 million
• EOL(S2) = 0.35(3) + 0.65(0) = GH¢ 1.05 million
• Since the decision-maker seeks to minimize the expected
opportunity loss, he must select course of action S1, as this
would produce the smallest expected opportunity loss.
STEP 1 STEP2
Experimental outcome
)

References

• Annan, J. (2014). Quantitative Analysis for Management.

Hammer Series, KNUST, Kumasi.
• Sharma, J.K. (2010). Quantitative Methods: Theory and
Applications, Macmillan Publishers India Limited
 THANK YOU

CHRISTIAN SERVICE UNIVERSITY COLLEGE,

KUMASI