DECISION ANALYSIS WITH

SAMPLE INFORMATION

Vaibhav Agrawal – 06
Devanshi Dhruva – 15
RV Kartik – 40
Aniket Sengar - 47
PROBLEM FORMULATION
First step in decision analysis is Problem Formulation.

Verbal Statement

Uncertain future events referred to as chance events

The outcome referred to as consequence

2 possible chance event outcomes are considered – strong

demand and weak demand.

The possible outcome for a chance event are referred to as

the states of nature.
PDC Ltd. purchased a land that will be the site of a new luxury condominium
complex. PDC plans to price the individual condominium units between
$300,000 and $1,400,000.

PDC commissioned preliminary architectural drawings for three different -

sized projects: one with 30 condominiums, one with 60 condominiums, and
one with 90 condominiums. The financial success of the project depends
upon the size of the condominium complex and the chance event concerning
the demand for the condominiums.

The statement of the PDC decision problem is to select the size of the new
luxury condominium project that will lead to the largest profit given the
uncertainty concerning the demand for the condominiums.
Decision Alternatives:

D1 – a small complex with 30 condominiums

D2 – a medium complex with 60 condominiums
D3 – a large complex with 90 condominiums

States of Nature

S1 – strong demand for the condominiums

S2 – weak demand for the condominiums
 Influence Diagrams
It is a graphical device that shows the relationship
among the decisions, the chance events and the
consequence.
Demand
Decision Nodes – Rectangle or Squares
Chance Nodes – Circles or Ovals
Consequence – Diamonds
Arcs – Connecting Nodes

Complex Size Profit

 Payoff Table
The consequence resulting from a specific combination of a
decision alternative and a state of nature is referred to as Payoff.

State Of Nature
Decision Alternative Strong Demand (S1) Weak Demand (S2)

Small Complex, D1 8 7
Medium Complex, 14 5
D2
Large Complex, D3 20 -9
 Decision Trees
A Decision Tree provides a graphical representation of the decision
making process. It shows the natural or logical progression that will
occur overtime.

Strong (S1)
Small (D1) 8
2
7
Weak (S2)

Strong (S1)
14
Medium (D2)
1 3
5
Weak (S2)

Strong (S1)
20
Large (D3) 4
-9
Weak (S2)
Decision Making without Probabilities

Best Payoff
Optimistic Approach

Worst Payoff
Conservative Approach

Opportunity Loss
Mini-Max Regret Approach
 Best Payoff
Optimistic Approach
Decision Alternative Maximum Payoff

Small Complex (d1) 8

Medium Complex (d2) 14

Large Complex (d3) 20

 Worst Payoff
Conservative Approach

Decision Alternative Minimum Payoff

Small Complex (d1) 7

Medium Complex (d2) 5

Large Complex (d3) -9

 Opportunity Loss
Mini-Max Regret Approach

Rij = |V*j – Vij|

Decision Alternatives Strong Demand s1 Weak Demand s2

Small Complex, d1 12 (20-8) 0 (7-7)

Medium Complex, d2 6 (20-14) 2 (7-5)

Large Complex, d3 0 (20-20) 16 [7-(-9)]

Decision Alternatives Maximum Regret

Small Complex, d1 12

Medium Complex, d2 6

Large Complex, d3 16
 Decision Making with Probabilities
Expected Value Approach

N = Number of states of nature

P(sj) = Profitability of state of nature j.

P(sj) >= 0, for all states of nature

ΣNj=1P(sj) = P(s1) + P(s2) + … + P(sN) = 1

Expected Value of a Decision Alternative EV(di) = ΣNj=1P(sj) Vij

 Expected Value of Perfect Information

To determine the potential value of the information, we begin by supposing

that study could provide perfect information about states of nature, that is,
we assume for a moment with certainty that, prior to the decision making
which state of nature is going to occur

EVPI=|EVwPI-EVwoPI|
EVPI=expected value of perfect information
EVwPI=Expected value with perfect information about the states of nature
EVPwoPI = Expected value without perfect information about the states of
nature
Expected Value of Perfect Information

If s1 would occur then, we will select

d3 and receive a payoff of $20 million

If s2 would occur then, we will select

d1 and receive a payoff of $7 million
 Risk Analysis
• Risk analysis helps the decision maker recognize
the difference b/w the expected value of a decision
alternative and payoff that might actually occur.

Probability
0.9
0.8
0.7
0.6
0.5 Probability

0.4
0.3
0.2
0.1
0
-9 20
 Sensitivity Analysis
• It is used to determine how changes in probabilities for
the states of nature or changes in payoffs affect the
recommended decision.
• It helps decision maker to understand which of the inputs
are critical to the choice of best alternative decision.

EV(d1) .2(8) + .8(7) =7.2

EV(d2) .2(14) + .8(5) =6.8

EV(d3) .2(20) + .8(-9) =-3.2

INFLUENCE DIAGRAM

RESERCH
STUDY DEMAND
RESULTS

RESEARCH COMPLEX
STUDY SIZE PROFIT
 DECISION TREE STRONG .94
SMALL WEAK .06
6
FAVOURABLE STRONG .94
0.23 MEDIUM WEAK .06
3 7
MARKET STRONG .94
RESEARCH LARGE WEAK .06
2 8
STRONG .35
SMALL WEAK .65
1 9
STRONG .35
MEDIUM WEAK .65
4 10
STRONG .35
UNFAVOURABLE .77
LARGE 11 WEAK .65

STRONG .8
SMALL WEAK .2
12
STRONG .8
MEDIUM WEAK .2
5 13 STRONG .8
NO MARKET RESEARCH
LARGE WEAK .2
14
• EV(node 6)=.94*8+.06*7=7.94
• EV(node 7)=.94*14+.06*5=13.46
• EV(node 8)=.94*20+.06*-9=18.26
• EV(node 9)=.35*8+.65*7=7.35
• EV(node 10)=.35*14+.65*5=8.15
• EV(node 11)=.35*20+.65*-9=1.15
• EV(node 12)=.80*8+.20*7=7.8
• EV(node 13)=.80*14+.20*5=12.2
• EV(node 14)=.80*20+.20*-9=14.2

• =>EV(node 2)=.77EV(node 3)+.23EV(node 4)

=.77*18.26+.23*8.15=15.93
EXPECTED VALUE AND EFFICIENCY

• Expected value of sample information

EVSI=mod[EVwSI-EVwoSI]
EVwSI-expected value with sample information
EVwoSI-expected value without sample information
=15.93-14.2=1.73
• Efficiency of sample information
E=(EVSI/EVPI)*100
EVPI-expected value with perfect information
=(1.73/3)*100=54.1%
Thank you