The Decision Process in Operations

• Decision making is inevitable in Operations Management

• Good decision making is sometimes based on logic, considers available
data and possible alternatives
Our focus will be on analytical decision-making using models, objectives
and quantifiable variables.
• Decision Tables and Decision trees are two OM tools that will be
discussed.
• They are useful in new-product analysis, location planning, capacity
planning etc.
 Fundamentals of Decision Making
• All decision makers are faced with “alternatives” and “states
of nature”.

Terms to be used in the module:

• Alternatives – a course of action or strategy that may be chosen by
decision maker( carrying or not carrying an umbrella tomorrow)
• State of nature : situation over which the decision maker has little or
no control (e.g. tomorrow’s weather)
Symbols to be used in a decision tree
• - decision node from which several alternatives are made

• - a state of –nature node out of which one state of the nature

will occur
Example 1:
Getz Products company is investigating the possibility of
producing and marketing backyard storage sheds.
Undertaking this project would require the construction
of either a large or a small manufacturing plant. The
Market for the product produced- storage sheds- could
be either favourable or unfavourable . Getz, of course
has the option of not developing the new product line at
all.
Getz is interested in building a decision tree. How should the
decision tree be built?
A simple decision tree
(Example Creating a simple decision tree)
Example 2 : Decision Table
Getz Products now wishes to organize the decision tree information in
example 1 above into a table. With a favorable market, a large facility will give
Getz Products a net profit of $200,000. If the market is unfavorable a
$180,000 net loss will occur. A small plant will result in a net profit of
$100,000 in a favorable market, but a net loss of $20,000 will be encountered
if the market is unfavorable. How should Getz proceed to that?

The Toughest part of a decision table is obtaining the data to analyze

 Types of Decision-Making Environments

• Decision making under uncertainty

• Decision making under risk
• Decision making under certainty

Decision making under uncertainty

• There is uncertainty about the state of nature in the decision

environment (i.e. we cannot assess probabilities for each
possible outcomes).
Decision making under uncertainty
• The only option is either to use:
• Maximax: locate the alternative with the highest possible gain
(optimistic decision)
• Maximin : locate the alternative with least possible loss (Pessimistic
decision)
• Equally likely: finds the alternative with the highest average outcome
i.e. calculate average outcome for each alternative.
Example 3 : Decision Making under uncertainty using inputs from
example 2 above
Decision making under Risk
• Decision making under probabilities ( more common)
• Several possible states of nature with assumed probabilities
• States of nature must be mutually exclusive, and their probabilities must
sum up to 1.
• Given a decision table where we have conditional values and probabilities
for the states of nature we can determine expected monetary value (EMV)
for each alternative
• Select the Maximum (EMV)
• EMV equation

𝑬𝑴𝑽 𝑨𝒍𝒕𝒆𝒓𝒏𝒂𝒕𝒊𝒗𝒆 𝒊 =
𝒑𝒂𝒚𝒐𝒇𝒇 𝒐𝒇 𝟏𝒔𝒕 𝒔𝒕𝒂𝒕𝒆 𝒐𝒇 𝒏𝒂𝒕𝒖𝒓𝒆 × 𝑷𝒓𝒐𝒃𝒂𝒃𝒊𝒍𝒊𝒕𝒚 𝒐𝒇 𝟏𝒔𝒕 𝒔𝒕𝒂𝒕𝒆 𝒐𝒇 𝒏𝒂𝒕𝒖𝒓𝒆 +
𝒑𝒂𝒚𝒐𝒇𝒇 𝒐𝒇 𝟐𝒏𝒅 𝒔𝒕𝒂𝒕𝒆 𝒐𝒇 𝒏𝒂𝒕𝒖𝒓𝒆 × 𝑷𝒓𝒐𝒃𝒂𝒃𝒊𝒍𝒊𝒕𝒚 𝒐𝒇 𝟐𝒏𝒅 𝒔𝒕𝒂𝒕𝒆 𝒐𝒇 𝒏𝒂𝒕𝒖𝒓𝒆 +
⋯ + (𝑷𝒂𝒚 𝒐𝒇𝒇 𝒐𝒇 𝒍𝒂𝒔𝒕 𝒔𝒕𝒂𝒕𝒆 𝒐𝒇 𝒏𝒂𝒕𝒖𝒓𝒆) × (𝑷𝒓𝒐𝒃𝒂𝒃𝒊𝒍𝒊𝒕𝒚 𝒐𝒇 𝒍𝒂𝒔𝒕 𝒔𝒕𝒂𝒕𝒆 𝒐𝒇 𝒏𝒂𝒕𝒖𝒓𝒆
Calculate Expected Monetary Value EMV (Example 4)

• EMV ( Alternative 1) = (0.6) ($200,000) + (0.4)(-$180,000) = $48,000

• EMV ( Alternative 2) = (0.6) ($100,000) + (0.4)(-$20,000) = $52,000
• EMV ( Alternative 3) = (0.6) ($0) + (0.4)(-$0) = $0
Alternative 2 gives the maximum EMV
Decision making under Certainty

• We deal with the concept of Expected value of perfect information (EVPI)

• We are interested in the value of perfect information obtainable from any
means.
• i.e upper bound on what you are willing to pay to obtain perfect
information from any source
• EVPI : The difference between the pay off under perfect information and
the pay off under risk
• EVPI = (Expected value with Perfect information) – (Maximum EMV)
• Expected value with Perfect information (EVwPI)
• EVwPI = ( Best outcome of 1st state of nature) × (Probability of 1st state of
nature) +(Best outcome of 2nd state of nature) × (Probability of 2nd state
of nature) +…+ Best outcome of last state of nature) × (Probability of last
state of nature)
• The expected (average) return if perfect information is available
• Maximum (EMV ) earlier discussed , is based on the alternatives
• Example 5 : Using previous example and the equation for EVPI how do you
obtain EVPI?
EVPI = (EVwPI) – (Maximum EMV)
EVPI = ?
To calcualte EVPI you must know the values of EVwPI and Maximum EMV
EVwPI?
Maximum EMV?
EVwPI . First identify the numbers of states of nature you have in the problem.
1. favourable outcome
2. unfavourable outcome
These are the two(2) states of nature you have in the problem above
❑ The best out come from all state of nature 1 ( favourable outcome ) i.e. From (
100,000; 200,000 and 0) is 200,000
❑ The best out come from all state of nature 2 (unfavourable outcome ) i.e. from -
180,000; -20,000 and 0) is 0
EVwPI = ($200,000 X 0.6) + ( 0 x 0.4) = $120,000
EVwPI = $120,000
What is Maximum EMV? Go to example 4 = $52,000
EVPI = $120,000 - $52,000 = $68,000
 Decision trees
• Unlike the decision table
• Decision table is convenient for problems having one set of decisions and
one set of states of nature
• Decision tree is suitable for problems with sequential decisions and states
of nature
• A decision tree is a graphic means of analyzing decision alternatives and
states of nature. The Expected Monetary Value (EMV) is the most
commonly used criterion for the analysis
• Five steps for analyzing problems with decision trees.
1. Define the problem
2. Structure or draw the decision tree
3. Assign probabilities to the states of nature
4. Estimate pay offs for each possible combination of decision
alternatives and states of nature
5. Solve the problem by computing the EMV for each state of nature
node ( Computed by working backwards)
Questions
( refer to 12th or 13th Edition of prescribed text)
Questions A.1, A.2, A.5, A.7, A.8, A.15