2 12

Recap of Last Lecture In-class Exercise: Café du Donut

• Poisson distribution à number of arrivals • Monetary Payoff (Profit) Table
▫ Relationship with binomial distribution
• Exponential distribution à time • Cost = $40, revenue = $60
▫ Relationship with Poisson distribution
D=4 D=5 D=6 D=7 D=8 D=9 D = 10 EMV
• Uniform distribution
• Normal distribution Q=6 0 60 120 120 120 120 120 105
▫ Standard normal distribution and Z table Q=7 -40 20 80 140 140 140 140 104
• Steps in decision making Prob. 0.05 0.15 0.15 0.20 0.25 0.10 0.10
▫ Define the problem
▫ List all possible alternatives, states of nature, and corresponding
payoff for each combination
• Should we reduce the order size from 6 to 5? What is the EMV of Q=5?
▫ Select a decision theory model and make the decision
• Decision making under certainty
• Decision making under risk • If we can only choose between 6 and 7, what is the EVPI?
▫ Maximize EMV & Minimize EOL
▫ EVPI = EVwPI – max EMV or EVPI = min EOL
11
In-class Exercise: Café du Donut
• The Café buys donuts each day for $40 per carton of 20 dozen
Chapter 02 donuts. Any cartons not sold are thrown away at the end of
the day. If a carton is sold, the total revenue is $60.
Decision Analysis DAILY DEMAND PROBABILITY CUMULATIVE
(CARTONS) PROBABILITY
IIMT3636 • The original plan 4 0.05 0.05
Faculty of Business and Economics is to order 6 5 0.15 0.2
The University of Hong Kong cartons per day. 6 0.15 0.35
Should the Café 7 0.20 0.55
Instructor: Dr. Yipu DENG
increase the 8 0.25 0.8
9 0.10 0.9
order size to 7?
10 0.10 1.0
Total 1.00
 15 17
Decision Making under Risk Sensitivity Analysis in Excel
EMV
Point1: 0=120,000p
• Step 1: setup the payoff table (data and formulas)
$300,000 • Step 2: setup the data table
Point2: 380,000p ▫ Set a list of values in the first column for the parameter to be
$200,000 EMV (large plant) explored, except for the first row.
Point 2 380,000p-180,000
0.45 ▫ Reference the output values in the first row, starting from the
$100,000
Point 1
EMV (small plant) second column.
120,000p-20,000
• Step 3: generate the one-way data table
0 EMV (do nothing)
0 ▫ Select the entire data table.
.167 .615 1
▫ Click: DATA -> What-If Analysis -> Data Table.
–$100,000 Values of p
▫ Set the Column input cell to the parameter cell in the original
model.
–$200,000
13 16
Decision Making under Risk Results of Sensitivity Analysis
• If the estimation of probability is changed, how will John change his
decision?
• A sensitivity analysis is needed! It investigates how our decision
BEST ALTERNATIVE RANGE OF P VALUES
might change given a change in the problem data.
STATE OF NATURE Construct a large plant >0.615
FAVORABLE UNFAVORABLE EMV Construct a small plant 0.167 - 0.615
ALTERNATIVE MARKET (profit in $) MARKET (profit in $) (in $1,000) Do nothing <0.167
Construct a large plant 200,000 –180,000 380p – 180
Construct a small plant 100,000 –20,000 120p – 20
Do nothing 0 0 0
Probability p 1–p
 19 4
In-Class Exercise Decision Making under Uncertainty
• Given Opportunity Loss Table What if we do not know the probabilities for all states of
State I State II nature?
Option A 5 1
Option B 0 3
Option C 6 0
• Maximax (optimistic)
Probability 0.3 0.7 • Maximin (pessimistic)
Payoff table
• How to restore the payoff table? • Criterion of realism (Hurwicz)
State I State II • Equally likely (Laplace)
Option A 1 3
EVwPI = 6(0.3) + 4(0.7) = 4.6 • Minimax regret Opportunity loss table
Option B 6 1
Option C 0 4
• What is the EVwPI?
18 3
In-Class Exercise In-class Exercises
• Assume directly measuring monetary payoff is infeasible • The Monty Hall Problem Revisited
▫ Suppose you're on a game show, and you're given the choice of three doors:
• Opportunity Loss Table Behind one door is a car; behind the others, goats. You pick a door, say No. 1, and
the host, who knows what's behind the doors, opens another door, say No. 3,
State I State II which has a goat. He then says to you, "Do you want to pick door No. 2?" Is it to
your advantage to switch your choice?
Option A 5 1
• Timeline
Option B 0 3
• Payoff table (payoff = 1 if you get a car; 0 otherwise)
Option C 6 0
Given door 1 is Car behind Car behind Car behind Expected
Probability 0.3 0.7 chosen door 1 door 2 door 3 Value
Switch 0 1 1 2/3
• Which is the option that maximizes EMV? Do not switch 1 0 0 1/3
Probability 1/3 1/3 1/3