ADM 2302 [Q]

Business Analytics
DGD11: Decision Analysis part II
Sicen Li
sli302@uottawa.ca
For today…

9.22, 9.23, 9.26, A3

9.22 (9.21 Cont.)
Silicon Dynamics
Decision Analysis
9.21 – Silicon Dynamics (revisit)
Silicon Dynamics has developed a new computer chip that will enable it to begin producing and
marketing a personal computer if it so desires. Alternatively, it can sell the rights to the computer
chip for $15 million. If the company chooses to build computers, the profitability of the venture
depends on the company’s ability to market the computer during the first year. It has sufficient
access to retail outlets that it can guarantee sales of 10,000 computers. On the other hand, if this
computer catches on, the company can sell 100,000 machines. For analysis purposes, these two
levels of sales are taken to be the two possible outcomes of marketing the computer, but it is unclear
what their prior probabilities are. The cost of setting up the assembly line is $6 million. The
difference between the selling price and the variable cost of each computer is $600.
9.21 – Silicon Dynamics (revisit)
a). Develop a decision analysis formulation of this problem by identifying the decision alternatives, the states of nature,
and the payoff table.

b). Construct a decision tree for this problem by hand.

Sell 10,000
0
Build Computers

Sell 100,000
54

Sell Rights
15
9.22 – Silicon Dynamics
Reconsider Problem 9.21. Management of Silicon Dynamics now is considering doing full-fledged
market research at an estimated cost of $1 million to predict which of the two levels of demand is
likely to occur. Previous experience indicates that such market research is correct two-thirds of the
time (assuming the prior probabilities of the two levels of sales are both 0.5)

a). Find the expected value of perfect information for this problem.

EP(with perfect information) = (0.5)(54) + (0.5)(15) = $34.5 million

EVPI = EP(with perfect information) – (EP without more information)

= 34.5 – 27 = $7.5 million.

b). Does the answer in part a indicate that it might be worthwhile to perform this market research?

Since the market research will cost $1 million it might be worthwhile to perform it.
c). Obtain the posterior probabilities of the two levels of demand for each of the two possible outcomes of the
market research.

Given
• Prior probabilities : P(market demand) the probability values before new information
• Conditional probabilities: P(test result | market demand) that can be estimated based on
past historical data

Estimate
• Revised (posterior) probabilities : P(market demand | test result) that revises prior
probability based on the new information of test result
Probability Calculation
Report P(sell x amount | 100k report)
State of Nature Conditional Probability Prior Probability Joint Probability Posterior Probability
Good report (sell 100k) Sell 100k 0.666666667 0.5 0.333333333 0.666666667
Sell 10k 0.333333333 0.5 0.166666667 0.333333333
P(good report) 0.5

P(Sell x amount | bad/10k report)

State of Nature Conditional Probability Prior Probability Joint Probability Posterior Probability
Bad report (sell 10k) Sell 100k 0.333333333 0.5 0.166666667 0.333333333
Sell 10k 0.666666667 0.5 0.333333333 0.666666667
P(bad report) = 0.5
9.23 (9.22 Cont.)
Drawing time:)
Decision Analysis
 The management
of Silicon
Dynamics now
wants to see a
decision tree
displaying the
entire problem.

The optimal policy is to do no market research and build the computers. The expected payoff is $27 million.
Find the expected value of sample information. How large
can the cost of doing full-fledged market research be and
still be worthwhile?

EVSI = EP(with information) – EP(without information)

= 27 – 27 = 0.
The information has no value.
9.26
Leland University
Decision Analysis
9.26 – Leland University
The Athletic Department of Leland University is considering whether to hold an extensive campaign
next year to raise funds for a new athletic field. The response to the campaign depends heavily on
the success of the football team this fall. In the past, the football team has had winning seasons 60
percent of the time. If the football team has a winning season (W) this fall, then many of the alumni
will contribute and the campaign will raise $3 million. If the team has a losing season (L), few will
contribute, and the campaign will lose $2 million. If no campaign is undertaken, no costs are
incurred. On September 1, just before the football season begins, the Athletic Department needs to
make its decision about whether to hold the campaign next year.
9.26 – Leland University
a). Develop a decision analysis formulation of this problem by identifying the decision alternatives, the states of
nature, and the payoff table.

State of Nature
Alternative Winning Season Losing Season
Hold campaign $3 million –$2 million
Don’t hold campaign 0 0
Prior Probabilities 0.6 0.4

b). According to Bayes’ decision rule, should the campaign be undertaken?

A B C D E
1 Payoff Table ($millions) Expected
2 State of Nature Payoff
3 Alternative Winning Season Losing Season ($millions)
4 Hold Campaign 3 -2 1
5 Don't Hold Campaign 0 0 0
6
7 Prior Probability 0.6 0.4

Choosing to hold the campaign maximizes the expected payoff ($1 million)
9.26 – Leland University
c). What is the expected value of perfect information?

EP(with perfect information) = (0.6)(3) + (0.4)(0) = $1.8 million

EVPI = EP (with perfect info) – EP (without more info)

= $1.8 million – $1 million
= $800,000

With perfect information, Leland University should hold the campaign if they will
have a winning season and don’t hold the campaign if they will have a losing season.
A famous football guru William has offered to help evaluate
whether the team will have a winning season. For $100,000,
he will carefully evaluate the team throughout spring
practice and then throughout preseason workouts. William
then will provide his prediction on September 1 regarding
what kind of season, W or L, the team will have. In similar
situations in the past when evaluating teams that have
winning seasons 50 percent of the time, his predictions have
been correct 75 percent of the time. Considering that this
team has more of a winning tradition, if William predicts a
winning season, what is the posterior probability that the
team actually will have a winning season? What is the
posterior probability of a losing season? If William predicts a
losing season instead, what is the posterior probability of a “Pay me $100,000 and I will tell you something”
winning season? Of a losing season? Also, construct a - William
decision tree and solve it.
Probability Calculation
Find the expected value of sample information. If the fee
for hiring William is open to negotiation, how large can
William’s fee be and still be worthwhile?

EVSI = EP(with information) – EP(without information)

= 1.15 – 1 = 0.15
The fee can be as high as $150,000 and the information
would still be worthwhile.
Assignment 3
any questions?