Introduction to Management

Science
Monday 21st November 2022
Recap
• Important dates
• Third term exam (Monday 5th December)
• Queuing Models
• Decision Analysis
• Payoff matrices
• Non-probabilistic methods
• Probabilistic methods
• Decision Trees
• Final Project Deliverable (Sunday 4th December 11:55pm on LMS)
• Final model and slides are due on the 4th
• Final 5-minute presentation will take place (Saturday 10th December – ALL DAY) – ROOM
203
Recap
• Queuing Models
• One example on MM1 queues with finite population
• Decision Analysis
• Simplifying, giving a structure to the decision making process
• Discussion on good decisions versus good outcomes
• Key concepts
• Outcomes/states of nature
• Criteria
• Alternatives
• Payoff matrix
• Non-probabilistic methods
• Maximax
• Maximin
Today’s discussion
• Evaluating regret
• Probabilistic methods
• EMV – expected monetary value
• EOL – expected opportunity loss/ regret
• Decision Trees
The Minimax Regret Decision Rule
• Compute the possible regret for each alternative
under each state of nature
• Identify the maximum possible regret for each
alternative
• Choose the alternative with the smallest maximum
regret
Anomalies within Minimax Regret
 Consider the following payoff matrix
State of Nature
Decision 1 2
A 9 2
B 4 6

 The regret matrix is:

State of Nature
Decision 1 2 MAX
A 0 4 4 <--minimum
B 5 0 5
 Note that we prefer A to B.
 Now let’s add an alternative...
Adding an Alternative
 Consider the following payoff matrix
State of Nature
Decision 1 2
A 9 2
B 4 6
C 3 9
 The regret matrix is:
State of Nature
Decision 1 2 MAX
A 0 7 7
B 5 3 5 <--minimum
C 6 0 6
 Now we prefer B to A???
 Probabilistic Methods
• Assign probabilities of likelihood of occurrence for various
states of nature
• Use historical data

• For one-time decision problems, such probabilities don’t exist

• Use subjective probabilities based on interviews with one or more
domain experts

• We will focus on techniques that can be used once appropriate

probability estimates have been obtained
 Expected Monetary Value
 Selects alternative with the largest expected
monetary value (EMV)

 EMVi is the average payoff we’d receive if we faced the

same decision problem numerous times and always
selected alternative i.
EMV Caution
• The EMV rule should be used with caution in one-time
decision problems

State of Nature
Decision 1 2
A 15,000 -5,000
B 5,000 4,000
Probability 0.5 0.5
 Expected Regret/Opportunity Loss
 Selects alternative with the smallest expected regret
or opportunity loss (EOL)
The Expected Value
of Perfect Information
• Suppose we could hire a consultant who could predict
the future with 100% accuracy
• 40% of the time the consultant would indicate airport
construction at location A
• 60% of the time at location B

• With such perfect information, Magnolia Inns’ average

payoff would be:
EV with PI = 0.4*$13 + 0.6*$11 = $11.8 (in
millions)
EVPI
• Without perfect information, the EMV was $3.4
million.
• The expected value of perfect information is
therefore,
EV of PI = $11.8 - $3.4 = $8.4 (in millions)
• In general,
EV of PI = EV with PI - maximum EMV
• What exactly is EVPI??
 A Decision Tree for Magnolia
Inns
Land Purchase Decision Airport Location Payoff
40%
-2 A 31 13
Buy A
1 60%
-18 B 6 -12
40%
3.4 A 4 -8
Buy B
2 60%
-12 B 23 11
2 40%
1.4
A 35 5
Buy A&B
3 60%
-30
B 29 -1
40%
0
A 0 0
Buy nothing
4 60%
0 B 0 0
Multi-Stage Decision Problem
• Steve Hinton, owner of COM-TECH, is considering whether to apply
for a $85,000 OSHA (Occupational Safety and Health Administration)
research grant for using wireless communications technology to
enhance safety in the coal industry.
• Steve would spend approximately $5,000 preparing the grant
proposal and estimates a 50-50 chance of receiving the grant.
• If awarded the grant, Steve would need to decide whether to use
microwave, cellular, or infrared communications technology.

 Steve would need to acquire some new equipment depending

on which technology is used…
Technology Equipment Cost
Microwave $4,000
Cellular $5,000
Infrared $4,000
COM-TECH (continued)
 Steve knows he will also spend money in R&D, but he doesn’t
know exactly what the R&D costs will be. Steve estimates the
following best case and worst case R&D costs and probabilities,
based on his expertise in each area.
Best Case Worst Case
Cost Prob. Cost Prob.
Microwave $30,000 0.4 $60,000 0.6
Cellular $40,000 0.8 $70,000 0.2
Infrared $40,000 0.9 $80,000 0.1
 How sensitive is the decision in the COM-TECH problem to
changes in the probability estimates?