OPERATIONS RESEARCH PROJECT

GROUP – 2
ABHISHEK NIGAM
ANUPAM ROY
DISHA KOTECHA
MAHESH OGANIA
PRIYA PATIL
SANYA RAWAL
SHUBHRA SALGAONKAR
STATISTICAL DECISION THEORY

 A general theory for the processing and use of statistical observations. In a broader
interpretation of the term, statistical decision theory is the theory of choosing an
optimal non-deterministic behavior in incompletely known situations.
 Decision-making means a process which results in the selection from a set of
alternative courses of action, that course of action which is regarded to meet the
objectives of the decision problem more satisfactorily as compared to others.
 Process of decision making includes: Defining the problem, Analysis of the problem,
Identification of alternatives, Evaluation of alternatives, Decision environment.
TERMS AND TERMINOLOGIES USED

 Goals: Objectives which the decision maker wants to achieve by his actions.
 Acts: Acts are the actions being considered by the agent or the decision maker.
Acts or alternatives- denoted by a1,a2,a3.
 Events: Events are occurrences taking place outside the control of the agent.
Events- denoted by e1,e2,e3.
 Pay off-measures the net benefit to decision maker, which results from a given combination.
 Outcomes: Outcomes are the result of the occurrence of acts and events.
 Opportunity loss or regret-the difference between pay off realized and the maximum
payoff which could have been realized if another strategy was chosen.
 DECISION MAKING ENVIRONMENTS

Decision under uncertainty Decision under risk

 The choice of a decision is very largely based on  Under this condition, the decision maker faces
company’s policy, experience and the judgment of several events and he cannot predict the
the decision maker. The methods used in it are: outcome of an event.

 Maxi-max criterion  Expected monetary value criterion(EMV)

 Mini-max criterion  Expected opportunity loss criterion(EOL)

 Coefficient of optimism criterion-Hurwicz  Expected value of perfect

information(EVPI)
 Laplace criterion
 Savage Criterion
LAPLACE CRITERION

 This criterion is based on the principle of insufficient reason and was developed by Thomas
Bayels and supported by Simon de Laplace.
 It is assumed that all states of nature will occur with equal probability
 Probabilities of each state of nature is given by 1/( number of states of nature)
 By using this criterion it is possible to convert a decision problem under certainty with equal
probability of each state of nature
ALGORITHM INVOLVED

 Assign equal probabilities to each payoff of a strategy

 Determine the expected pay off value for each alternative
 Select the alternative which corresponds to the maximum payoff or minimum cost
EXAMPLE

Example:
A farmer wants to decide which of the three crops he should plant on his 100 Acre farm.
The profit from each is dependent on the rainfall during the growing seasons. The farmer has
categorized the amount of rainfall as high, medium, low. His estimated profit for each is show
in the table:
Rainfall Crop A Crop B Crop C

High 8000 3500 5000

Medium 4500 4500 5000

Low 2000 5000 4000

SOLUTION

 Assign equal probabilities i.e. 1/3. The expected pay off is calculated for each alterative:
 E (Crop A)=1/3(8000)+1/3(4500)+1/3(2000)= 4833
 E (Crop B)=4333
 E (Crop C)=4666
 Hence this criterion selects crop A.
MAXIMIN (MINIMAX) CRITERION

 Maximin (Minimax) model is a non-probabilistic decision-making model according to which

decisions are ranked on the basis of their worst-case outcomes – the optimal decision is
one with the least worst outcome.

 The Maximin criterion is a pessimistic / conservative approach.

 It suggests that the decision maker examines only the minimum payoffs of alternatives and
chooses the alternative whose outcome is the least bad.
 DECISION MAKING
 If v(ai, sj) is loss, then we select the action that corresponds to the following minimax criterion:

 If v(ai, sj) is gain, then we select the action that corresponds to the following maximin criterion:
STEPS INVOLVED

1. Determine the objective (that is, whether it is a loss or gain we are interested in)

2. Calculate Row Max or Row Min based on the objective.

3. Choose the best alternative with the minimum maximum loss.

 ILLUSTRATION
 Ankur is an intelligent student and gets good marks, provided he studies the night before the exam. But
there is a problem, Ankur’s friends are having an all-night party in which he is invited. Ankur has 3
options:
this is, a1 = Party all night
a2 = Divide the night equally between studying and partying
a3 = Study all night
Tomorrow’s OR exam can be easy (S1), moderate (S2), or tough (S3), depending on the
PROFESSOR’s MOOD.
Ankur anticipates the following marks (out of 100):
SOLUTION ANKUR WILL GO WITH (BASED ON MAXIMIN
CRITERION)

 The maximin criterion produces the following matrix:

Row Min

40

81

82 Maximin

 Therefore Ankur will STUDY ALL NIGHT (a3)

 HURWICZ’S CRITERION (CRITERION OF REALISM)

 Hurwicz criterion (weighted average of criterion), suggested by Leonid Hurwicz in 1951,

selects the minimum and the maximum payoff to each given action x.
 The Hurwicz criterion attempts to find a middle ground between the extremes posed by
the optimist and pessimist criteria. Instead of assuming total optimism or pessimism, Hurwicz
incorporates a measure of both by assigning a certain percentage weight to optimism and
the balance to pessimism.
 This concept allows the decision maker to take into account both the maximum and
minimum for each alternative and assign them weights according to his degree of optimism
(or pessimism). The alternative which maximizes the sum of these weighted payoffs is then
selected.
 This approach attempts to strike a balance between the Maximax and Maximin criteria.
STEPS TO FOLLOW:

 1. Choose an appropriate degree of optimism α, so that (1-α) represents the degree of

pessimism. α is called coefficient or index of optimism.
 2. Determine the maximum as well as minimum of each alternative and obtain
 P = α.(Maximum/Best Payoff) + (1-α). (Minimum/Worst Payoff)
 3. Choose the alternative that yields the maximum value of P.

 When α=0, the criterion is too pessimistic; when α=1, it is too optimistic. A value of α
between zero and one may be selected depending upon whether the decision-maker leans
towards pessimism or optimism. A value of α=1/2 seems to be a reasonable choice.
HURWICZ CRITERION EXAMPLE

Economy
Alternatives Growing Stable Declining
Bonds 40 45 5
Stocks 70 30 -13
Mutual Funds 53 45 -5

Given: α=0.3 Therefore, (1- α)=0.7

Alternatives Growing Stable Declining Weighted Average
Bonds 40 45 5 0.3(45)+0.7(5)=17
Stocks 70 30 -13 0.3(70)+0.7(-13)=11.9
Mutual Funds 53 45 -5 0.3(53)+0.7(-5)= 12.4

Select highest weighted average value.

Decision: Invest in Bonds
 Savage Regret Criterion

• The Regret criterion focuses on avoiding regrets that may result from making a
non‐optimal decision.

• Regret is defined as the opportunity loss r(a(i),θ(j)) to the decision maker if action
alternative a(i) is chosen and state of nature θ(j) happens to occur.

• Opportunity loss is the payoff difference between the best possible outcome under θ(j)
and the actual outcome resulting from choosing a(i)

• Note that opportunity losses are defined as nonnegative numbers.

• The best possible OL is zero (no regret) and the higher the OL value, the greater the
regret.
 Steps to calculate

1. First we have to calculate the Opportunity Loss table TIP:

• The primary advantage of the
2. We have to calculate the maximum opportunity loss for mini-max regret decision
each alternative criterion is its relative
simplicity.
3. At the end we choose the alternative with the
minimum maximum loss. Thus A3.
• This criterion’s disadvantages
include its emphasis on the
worst possible outcome

• It ignores risk as represented

by an outcome’s probability of
occurring
 EXPECTED MONETARY VALUE
 The expected monetary value is how much money you can expect to make from a certain
decision
 Expected monetary value technique (EMV) is a risk management technique to help quantify
and compare risks in the project.
 It is a quantitative risk analysis technique
 Expected Monetary Value (EMV) uses the probabilities to calculate the average payoff for
each alternative
 EMV for the specified course of action is the weighted average payoff, weighted according to
the probability of occurance of that course of action
EMV= ∑[(probability of outcome) x (payoff of outcome)]
STEPS INVOLVED

1. Assign a probability of occurrence for the risk.

2. Assign monetary value of the impact of the risk when it occurs.
3. Multiply Step 1 and Step 2.
4. The value obtained after performing Step 3 is the Expected Monetary Value.
5. This value is positive for opportunities (positive risks) and negative for threats (negative
risks).
ILLUSTRATIVE EXAMPLE
ABC company plans to launch a new product which requires expansion of their manufacturing
facility
Alternatives available:
• Build a large plant
• Build a small plant
• Do nothing
Outcomes: Demand for new product will be high, moderate, or low
Suggest what should be the decision of the company based on expected value analysis
 PAYOFFS

Assumptions

1. All the products

manufactured in the
respective plants are
sold in the market
2. The table shows the
revenue collected after
the sale of new product
Probabilities of outcomes
High demand: 0.3
Moderate demand: 0.5
Low demand: 0.2
CALCULATION OF EMV

 If large plant is constructed

(200,000*0.3)+(100,000*0.5)+(-1,20,000*0.2) = 86,000
 If small plant is constructed
(90,000*0.3)+(50,000*0.5)+(-20,000*0.2) = 48000
 If no plant is constructed, new product cannot be produced and hence no revenue.
Decision
 Since the expected monetary value is highest in case of large plant, that alternative is to
be chosen
EXPECTED OPPORTUNITY LOSS (EOL)

 One more way of maximizing monetary value is to minimize the expected opportunity loss
or expected value of regret.
 The expected opportunity loss (EOL) for a particular course of action is determined by
taking the difference between the payoff value of the most favourable course of action and
some other course of action.
 Thus, opportunity loss can be obtained separately for each course of action by first obtaining
the best state of nature for the prescribed course of action and then taking the difference
between that best outcome and each outcome for those courses of action.
 Pay Off Table
Profit in $000’s
Investment (States of Nature)
Choice Strong Stable Weak
(Action) Economy Economy Economy
Large factory 200 50 -120
Average factory 90 120 -30
Small factory 40 30 20

Opportunity Loss Table

Opportunity Loss in $000’s
Investment (Events)
Choice Strong Stable Weak
(Action) Economy Economy Economy
Large factory 0 70 140 210
Average factory 110 0 50 160
Small factory 160 90 0 250
Hence we select 160 as the best option as it offers the least loss in payoff. So we
will go with the Average factory
EXPECTED VALUE WITH PERFECT INFORMATION (EVPI)

 EVPI helps to determine the worth of an insider who possesses perfect information.
 The expected value with perfect information is the amount of profit foregone due to
uncertain conditions affecting the selection of a course of action.
 Given the perfect information, a decision-maker is supposed to know which
particular state of nature will be in effect.
HOW TO CALCULATE EVPI?

 Expected value with perfect information (EVPI) is equal to difference between

Expect value with perfect information (EVwPI) and expected value without perfect
information(EVwoPI)
 Expected value without perfect information is the maximum expected monetary
value (EMV) from the table
 So , EVPI = EVwPI – EVwoPI or EVPI = EVwPI – Max EMV
EXAMPLE

Payoffs
SOLUTION
 First we calculate the Emv and find the maximum value which will be equal to EMwoPI

EMV (BONDS) = 0.2(40) + 0.5(45) + 0.3(5) = 32

EMV (Stocks) = 0.2(70)+0.5(30)+0.3(-13) = 25.1

EMV(Mutual funds) = 0.2(53) + 0.5(45)+0.3(-5) = 31.6

NOW WE CALCULATE EVWPI

EVwPI = 70(0.2) + 45(0.5) + 5(0.3) = 38

EVPI = EVwPI – EVwoPI

EVwPI=38
EVwoPI=32

EVPI= 38-32 =6
THANK YOU