Sie sind auf Seite 1von 99

Decision Models

Chapter 6

6.1 Introduction to Decision Analysis


The field of decision analysis provides a framework for making important decisions. Decision analysis allows us to select a decision from a set of possible decision alternatives when uncertainties regarding the future exist. The goal is to optimize the resulting payoff in terms of a decision criterion.
2

6.1 Introduction to Decision Analysis


Maximizing expected profit is a common criterion when probabilities can be assessed. Maximizing the decision makers utility function is the mechanism used when risk is factored into the decision making process.
3

6.2 Payoff Table Analysis


Payoff Tables
Payoff table analysis can be applied when:
There is a finite set of discrete decision alternatives. The outcome of a decision is a function of a single future event.

In a Payoff table The rows correspond to the possible decision alternatives. The columns correspond to the possible future events. Events (states of nature) are mutually exclusive

TOM BROWN INVESTMENT DECISION


Tom Brown has inherited $1000. He has to decide how to invest the money for one year. A broker has suggested five potential investments.
Gold Junk Bond Growth Stock Certificate of Deposit Stock Option Hedge
5

TOM BROWN
The return on each investment depends on the (uncertain) market behavior during the year. Tom would build a payoff table to help make the investment decision

TOM BROWN - Solution


Construct a payoff table. Select a decision making criterion, and apply it to the payoff table. Identify the optimal decision. Evaluate the solution.
S1 S2 S3 S4 D1 p11 p12 p13 p14 D2 p p p P
Criterio n

P1 P2 7 P3

The Payoff Table

Alte ative Larg RiseSm RiseN Ch g Sm Fall La eFall rn s e all o an e all rg Gold -100 100 200 300 0 Bon d 250 The states of nature are 200 150 -100 -150 Stock 500 mutually exclusive and-200 250 100 -600 collectively exhaustive. C/Daccou t n 60 60 60 60 60 Stock op tion 200 150 150 -200 -150
8

DJA is downDJA is down more DJA is up more DJA is up DJA [+300,+1000] moves [-300, -800] than 800 points than1000 points within [DefineStates of N of nature. the states re 300,+30 atu D cision e 0]

The Payoff Table


D cision e States of N re atu Alte ative Larg RiseSm RiseN Ch g Sm Fall La eFall rn s e all o an e all rg Gold -100 100 200 300 0 Determine Bon d 250 200 150 -100 -150 the set of Stock 500 250 100 -200 -600 possible C/Daccou t n 60 60 60 60 60 decision Stock op tion 200 150 -200 -150 alternative 150

s.

The Payoff Table


D ecision St es of N u at at re Alt at es Larg RiseSm RiseN Ch g ern iv e all o an eSm Fall Larg Fall all e Gold -100 100 200 300 0 Bon d 250 200 150 -100 -150 -100 250 200 150 -150 St ock 500 250 100 -200 -600 C/D accou t n 60 60 60 60 60 St op ion ock t 200 150 150 -200 -150 -150

The stock option alternative is dominated by the

10

6.3

Decision Making Criteria

Classifying decision-making criteria


Decision making under certainty.
The future state-of-nature is assumed known.

Decision making under risk.


There is some knowledge of the probability of the states of nature occurring.

Decision making under uncertainty.


There is no knowledge about the probability of the states of nature occurring.
11

Decision Making Under Uncertainty


The decision criteria are based on the decision makers attitude toward life. The criteria include the
Maximin Criterion - pessimistic or conservative approach. Minimax Regret Criterion - pessimistic or conservative approach. Maximax Criterion - optimistic or aggressive approach.

12

Decision Making Under Uncertainty - The Maximin Criterion

13

Decision Making Under Uncertainty - The Maximin Criterion


It fits both a pessimistic and a conservative decision makers styles. A pessimistic decision maker believes

This criterion is based on the worstcase scenario.

that the worst possible result will always occur. A conservative decision maker wishes to
14

TOM BROWN - The Maximin Criterion


To find an optimal decision
Record the minimum payoff across all states of nature for each decision. Th Identify the decision withethe maximum op t The Maxim in Criterion Minim um um minimum payoff. in Criterionim The Maxim Minim Decisions Large Rise Small rise No ChangeSmall aFall Large Fall Payoff ld Decisions Large Rise Small rise No ChangeSmallFall Large Fall Payoff Gold -100 100 200 300 ec 0 -100 Gold -100 100 200 300 i 0 -100 si Bond 250 200 150 -100 on Bond 250 200 150 -100 -150 -150 -150 -150 Stock 500 250 100 -200 Stock 500 250 100 -200 -600 -600 -600 -600 C/D account 60 60 60 60 60 60 60 60 60 60 60 C/D account 60
15

The Maximin Criterion spreadsheet

=MAX(H4: H7)

* FALSE is the range lookup argument in the VLOOKUP function in cell B11 since the values in column H are not in ascending order

=MIN(B4: F4) Drag to H7 =VLOOKUP(MAX(H4:H7),H4:I7, 2,FALSE)


16

The Maximin Criterion spreadsheet

I4

Cell I4 (hidden)=A4 Drag to I7 To enable the spreadsheet to correctly identify the optimal maximin decision in cell B11, the labels for cells A4 through A7 are copied into cells I4 through I7 (note that column I in the spreadsheet is hidden).

17

Decision Making Under Uncertainty - The Minimax Regret Criterion

18

Decision Making Under Uncertainty - The Minimax Regret Criterion


The Minimax Regret Criterion
This criterion fits both a pessimistic and a conservative decision maker approach. The payoff table is based on lost opportunity, or regret. The decision maker incurs regret by failing to choose the best decision.
19

The Minimax Regret Criterion

Decision Making Under Uncertainty - The Minimax Regret Criterion


To find an optimal decision, for each state of nature:
Determine the best payoff over all decisions. Calculate the regret for each decision alternative as the difference between its payoff value and this best payoff value.

For each decision find the maximum regret over all states of nature. Select the decision alternative that has 20 the minimum of these maximum

TOM BROWN Regret Table


Decision Large rise Sm allrise No changeSmallfall Large fall all all Decision Large rise Sm rise No changeSm fall Large fall -100 100Investing in Stock 200 300 0 Gold Gold -100 100 200 300 0 Bond 250 200 150 -100 -150 Bond 250 200 150 -100 -150 generates no regret when Stock 500 250 market exhibits -600 -200 Stock 500 250 100 -200 -600 the 100 60 60 60 60 60 C/D 60 60 60 60 60 C/D
Th e Payoff Table e Th Payoff Table

a large rise

TheRe t Ta gre ble D cision La rise Sm ll riseN cha e rge a o nge Sm ll fa La fa a ll rge ll 60 0 10 5 0 0 6 0 Gold build the Regret 0 20 5 Let us5 0 5 0 4 Table 2 0 0 1 Bond 0 0 10 0 50 0 60 6 Stock 21 40 4 10 9 10 4 20 4 0 C/D

TOM BROWN Regret Table


Decision Large rise Sm allrise No changeSmallfall Large fall all all Decision Large rise Sm rise No changeSm fall Large fall -100 100 Investing in gold 0 200 300 Gold Gold -100 100 200 300 0 Bond 250 200 150 -100 -150 Bon d 250 200 150 -100 -150 T generatesha regret of 600 Stock 500 250 100 e -200 -600 Stock 500 250 100 o -200 -600 when the market exhibits pt 60 60 60 60 60 C/D 60 60 60 60 60 C/D
The Payoff Tab le le The Payoff Tab

a large rise im 500 (-100) = 600 al de Th e Re re Tab le e gret le Max u m ax imm ci Th Re g t Tab M imu D e n Larg e riseSmallriseN o ch g eSmallfall Larg e fa Re g t e cisio Larg rise Smll riseN ch ane Sm fa Larg sioll Re re e a o an g all ll e fall g ret Dcisio n n 600 150 0 0 60 600 Go ld ld 600 150 0 0 60 600 Go 250 50 50 400 210 400 Bo n nd 250 50 50 400 210 400 Bod 0 0 100 500 660 660 St o o ck 0 0 100 500 660 660 Stck 22 440 190 140 240 0 440 C/D 440 190 140 240 0 440 C/D

The Minimax Regret spreadsheet

=MAX(B$4:B$ 7)-B4 Drag to F16 Cell I13 (hidden) =A13 Drag to I16 =MIN(H13: H16) =VLOOKUP(MIN(H13:H16),H13:I16,

=MAX(B14:F1 4) Drag to H18

23

This criterion is based on the best possible scenario. It fits both an optimistic and an aggressive decision maker. An optimistic decision maker believes that the best possible outcome will always take place regardless of the decision made. An aggressive decision maker looks for the 24 decision with the highest payoff (when payoff

Decision Making Under Uncertainty - The Maximax Criterion

Decision Making Under Uncertainty - The Maximax Criterion


To find an optimal decision.
Find the maximum payoff for each decision alternative. Select the decision alternative that has the maximum of the maximum payoff.

25

TOM BROWN - The Maximax Criterion


op tim al TheM xim x Crit rion a a e M xim a um D cision La rise Sm ll rise N cha e rge a o nge Sm ll fa La dec ll Pa a ll rgefa yoff -100 100 200 300 0 isio 300 Gold Bond 250 200 150 -100 -150 n 200
Stock C/D

Th e

500 60

250 60

100 60

-200 60

-600 60

500 60

26

Decision Making Under Uncertainty - The Principle


of Insufficient Reason
This criterion might appeal to a decision maker who is neither pessimistic nor optimistic.
It assumes all the states of nature are equally likely to occur. The procedure to find an optimal decision.
For each decision add all the payoffs. Select the decision with the largest sum (for 27

TOM BROWN - Insufficient Reason


Sum of Payoffs
Gold 600 Bond 350 Stock 50 C/D 300 Dollars Dollars Dollars Dollars

Based on this criterion the optimal decision alternative is to invest in gold. 28

Decision Making Under Uncertainty Spreadsheet


Payoff Table

template
Small Rise 100 200 250 60

Gold Bond Stock C/D Account d5 d6 d7 d8 Probability

Large Rise -100 250 500 60

No Change 200 150 100 60

Small Fall 300 -100 -200 60

Large Fall 0 -150 -600 60

0.2

0.3

0.3

0.1

0.1

RESULTS Criteria Maximin Minimax Regret Maximax Insufficient Reason EV EVPI

Decision C/D Account Bond Stock Gold Bond

Payoff 60 400 500 100 130 141

29

Decision Making Under Risk


The probability estimate for the occurrence of each state of nature (if available) can be incorporated in the search for the optimal decision. For each decision calculate its expected payoff.
30

The Expected Value Criterion


For each decision calculate the expected payoff as follows:

Decision Making Under Risk

Expected Payoff = (Probability)(Payoff) Expected Payoff = (Probability)(Payoff


(The summation is calculated across all the states of nature)

Select the decision with the best expected payoff

31

he op tim al Expected Th Exp e ected Valu Criterion de e cis fall Value D ecision Large riseSm rise N ch ge Sm fall Largeo all o an all i n -100 100 200 300 0 100 Gold 250 200 150 -100 -150 130 Bon d 500 250 100 -200 -600 125 Stock 60 60 60 60 60 60 C/D 0.3 0.3 0.1 0.1 Prior Prob . 0.2

TOM BROWN - The Expected Value Criterion T

.2)(250) + (0.3)(200) + (0.3)(150) + (0.1)(-100) + (0.1)(-150)

32

When to use the expected value approach


The expected value criterion is useful generally in two cases:
Long run planning is appropriate, and decision situations repeat themselves. The decision maker is risk neutral.

33

The Expected Value Criterion - spreadsheet Cell H4 (hidden)


= A4 Drag to H7

=MAX(G4: G7)

=SUMPRODUCT(B4:F4,$B$ 8:$F$8) Drag to G7

=VLOOKUP(MAX(G4:G7),G4:H7, 2,FALSE)

34

6.4 Expected Value of Perfect Information


The gain in expected return obtained from knowing with certainty the future state of nature is called:

Expected Value of Perfect Information (EVPI)


35

TOM BROWN - EVPI


T eE p ce V l eo P re tI f r ai n h - x e t d au f ef c nomto

e known with certainty that there will be a Large Rise in the


DcsoLarger riseS a r e ei i n L r e is ag e mll is N c ag o hn e S a f ll mll a L r ef ll ag a 1000 Gl od -1 0 10 0 20 0 30 0 0 Bn od 20 5 20 0 10 5 -1 0 0 -1 0 5 So k tc 50 0 20 5 10 0 -2 0 0 -6 0 0 CD / 6 6 0 6 0 6 0 6 0 2500 Po a . r bb 0 .2 0 .3 0 .3 0 .1 0 .1

Stock

the optimal decision would be to invest in... 50 Similarly, 0 60


36

TOM BROWN - EVPI


T eE p ce V l eo P re tI f r ai n h - x e t d au f ef c nomto

Dcso ei i n Gl od Bn od So k tc CD / Po a . r bb

L r er e ag is

1000 -1 0

Sare mll is

N c ag o hn e

S a f ll mll a

L r ef ll ag a

20 5 50 0 6 2500 0 .2

10 0 20 0 20 5 6 0 0 .3

20 0 10 5 10 0 6 0 0 .3

30 0 -1 0 0 -2 0 0 6 0 0 .1

0 -1 0 5 -6 0 0 6 0 0 .1

Expected Return with Perfect information = ERPI = 50 0 0.2(500)+0.3(250)+0.3(200)+0.1(300)+0.1(6 0) = $271 60 Expected Return without additional information =

37

6.5 Bayesian Analysis Decision Making with Imperfect Information


Bayesian Statistics play a role in assessing additional information obtained from various sources. This additional information may assist in refining original probability estimates, and help improve decision making. 38

Tom can purchase econometric forecast results for $50. The forecast predicts negative or Should Tom purchase the positive econometric growth. Forecast ? Statistics regarding the forecast When the stock market showed a... Th Foare: e r ca e st
predicted
La eRise Sm ll R rg a ise N Ch n e o ag Posit eecon g t iv . rowh N at eecon g t eg iv . rowh

TOM BROWN Using Sample Information

8% 0 2% 0

7% 0 3% 0

5% 0 5% 0

Sm ll Fa a ll

4% 0 6% 0

La eFa rg ll

0 % 10 0%

When the stock market showed a large rise the 39 Forecast predicted a positive growth 80% of the time

TOM BROWN Solution Using Sample Information


If the expected gain resulting from the decisions made with the forecast exceeds $50, Tom should purchase the forecast. The expected gain = Expected payoff with forecast EREV To find Expected payoff with forecast Tom should determine what to do when:
The forecast is positive growth,
40

TOM BROWN Solution Using Sample Information


Tom needs to know the following probabilities
P(Large rise | The forecast predicted Positive) P(Small rise | The forecast predicted Positive) P(No change | The forecast predicted Positive ) P(Small fall | The forecast predicted Positive) P(Large Fall | The forecast predicted Positive)

41

TOM BROWN Solution Bayes Theorem


Bayes Theorem provides a procedure to calculate these probabilities P(B|Ai)P(Ai)
P(Ai|B) =

P(B|A1)P(A1)+ P(B|A2)P(A2)++ P(B|An)P(A

Posterior Probabilities
Probabilities determined after the additional info becomes available.

Prior probabilities
Probability estimates determined based on current info, before the 42 new info becomes available.

TOM BROWN Solution Bayes Theorem

The tabular approach to calculating posterior probabilities for positive economical forec
States of

Nature Large Rise Sm Rise all No Change Sm Fall all Large Fall

Prior Prob.

0.2 0.3 0.3 0.1 0.1

Prob. Joint (State|Positive) Prob.


X

0.8 0.7 0.5 0.4 0

0.16 0.21 0.15 0.04 0

Posterior Prob.

0.286 0.375 0.268 0.071 0.000

The Probability that the forecast is positive and the stock market shows

43

TOM BROWN Solution Bayes Theorem

The tabular approach to calculating posterior probabilities for positive economical forec
States of

Nature Large Rise Sm Rise all No Change Sm Fall all Large Fall

Prior Prob.

0.2 0.3 0.3 0.1 0.1

Prob. Joint (State|Positive) Prob.


X

0.8 0.7 0.5 0.4 0

0.16 0.21 0.15 0.04 0

Posterior Prob.

0.286 0.375 0.268 0.071 0.000

0.16 0.56

The probability that the stock market shows Large Rise given that 44 the forecast is positive

TOM BROWN Solution Bayes Theorem

The tabular approach to calculating posterior probabilities for positive economical forec
States of

Nature Large Rise Sm Rise all No Change Sm Fall all Large Fall

Prior Prob.

0.2 X 0.8 = 0.16 0.286 0.3 0.7 0.21 0.375 Observe the revision in 0.3 0.5 0.15 0.268 0.1the prior probabilities 0.4 0.04 0.071 0.1 0 0 0.000

Prob. Joint (State|Positive) Prob.

Posterior Prob.

Probability(Forecast = positive) = .56


45

TOM BROWN Solution Bayes Theorem

The tabular approach to calculating posterior probabilities for negative economical forec
States of

Nature Large Rise Sm Rise all No Change Sm Fall all Large Fall

Prior Prob.

0.2 0.3 0.3 0.1 0.1

Prob. J oint (State|negative) Probab.

0.2 0.3 0.5 0.6 1

0.04 0.09 0.15 0.06 0.1

Posterior Probab.

0.091 0.205 0.341 0.136 0.227

Probability(Forecast = negative) = .44


46

Posterior (revised) Probabilities spreadsheet template


Ba ye sia n Ana lysis Indicator 1 Indicator 2 S tates P rior Conditional Joint P osterior S tates P rior Conditional Joint P osterior of Nature ProbabilitiesProbabilitiesP robabilitiesP robabilites of Nature P robabilitiesP robabilitiesP robabilities robabilites P Large Rise 0.2 0.8 0.16 0.286 Large Rise 0.2 0.2 0.04 0.091 S m all Rise 0.3 0.7 0.21 0.375 S m all Rise 0.3 0.3 0.09 0.205 No Change 0.3 0.5 0.15 0.268 No Change 0.3 0.5 0.15 0.341 S m all Fall 0.1 0.4 0.04 0.071 S m all Fall 0.1 0.6 0.06 0.136 Large Fall 0.1 0 0 0.000 Large Fall 0.1 1 0.1 0.227 s6 0 0 0.000 s6 0 0 0.000 s7 0 0 0.000 s7 0 0 0.000 s8 0 0 0.000 s8 0 0 0.000 P (Indicator 1) 0.56 P (Indicator 2) 0.44

47

This is the expected gain from making decisions based on Sample Information.

Expected Value of Sample Information EVSI

Revise the expected return for each decision using the posterior probabilities as follows:
48

TOM BROWN Conditional Expected Values


D cs n e i io Gl od Bn od So k tc CD / PSaeP s i e ( t t | o itv ) PSaen g tv ) ( t t | e ai e T er vs dpo a i ie p y f t b h e i e r b blit s a of a le
L r ers ag i e S alrs N c a g S alf l ml i e o h n e ml al L r ef l ag al 0 -1 0 5 -6 0 0 6 0 0 02 .2 7

-1 0 0 20 5 50 0 6 0 08 .2 6 09 .0 1

10 0 20 0 20 5 6 0 07 .3 5 00 .2 5

20 0 10 5 10 0 6 0 06 .2 8 04 .3 1

30 0 -1 0 0 -2 0 0 6 0 07 .0 1 03 .1 6

EV(Invest in. |Positive forecast) = GOLD =.286( )+.268( -100 )+.375( 200 100 300 )+.071( 0 $84 ) +0( ) = GOLD EV(Invest in . | Negative forecast) = -100 100 200 300 0 $120 49 =.091( )+.205( )+.341( )+.136( )

TOM BROWN Conditional Expected Values


The revised expected values for each decision:
Positive forecast forecast Negative

EV(Gold|Positive) = 84 EV(Gold| Negative) = 120 EV(Bond|Positive) = 180 EV(Bond| If the forecast = 65 If the forecast is Negativ Negative) is Positive Invest in Stock. Invest EV(Stock|Positive) = 250 in Gold. EV(Stock| Negative) = -37 50 EV(C/D|Positive) = 60 EV(C/D|

TOM BROWN Conditional Expected Values


Since the forecast is unknown before it is purchased, Tom can only calculate the expected return from purchasing it. Expected return when buying the forecast = ERSI = P(Forecast is positive)(EV(Stock|Forecast is positive)) + P(Forecast is negative)(EV(Gold|Forecast
is negative)) = (.56)(250) + (.44)(120) = $192.5
51

The expected gain from buying the forecast is: EVSI = ERSI EREV = 192.5 130 = $62.5 Tom should purchase the forecast. His expected gain is greater than the forecast cost.
52

Expected Value of Sampling Information (EVSI)

TOM BROWN Solution EVSI spreadsheet template


Payoff Table Large Rise -100 250 500 60 Small Rise No Change Small Fall Large Fall 100 200 300 0 200 150 -100 -150 250 100 -200 -600 60 60 60 60 s6 s7 s8 EV(prior) EV(ind. 1) EV(ind. 2) 100 83.93 120.45 130 179.46 67.05 125 249.11 -32.95 60 60.00 60.00 Gold Bond Stock C/D Account d5 d6 d7 d8 Prior Prob. Ind. 1 Prob. Ind 2. Prob. Ind. 3 Prob. Ind 4 Prob.

0.2 0.286 0.091

0.3 0.375 0.205

0.3 0.268 0.341

0.1 0.071 0.136

0.1 0.000 0.227

#### ### ## #### ### ##

0.56 0.44

RESULTS optimal payoff optimal decision EVSI = EVPI = Efficiency= Prior 130.00 Bond 62.5 141 0.44 Ind. 1 249.11 Stock Ind. 2 120.45 Gold Ind. 3 0.00 Ind. 4 0.00

53

6.6 Decision Trees


The Payoff Table approach is useful for a non-sequential or single stage. Many real-world decision problems consists of a sequence of dependent decisions. Decision Trees are useful in analyzing multi-stage decision
54

A Decision Tree is a chronological representation of the decision process. The tree is composed of nodes and branches.
Decision 1 ion nodeDecis t 1 Chance S 1) P( node
A branch emanating from a decision node P(S2) corresponds to a P( decision alternative. It S) 3 includes a cost or S 1) P( benefit value. A branch emanating from a P(S2)state of nature (chance) node corresponds to a P( S ) particular state of nature, 3 and includes the probability 55 of this state of nature.

Characteristics of a decision tree

s DeCo cis C o io n 2 st 2

BILL GALLEN DEVELOPMENT COMPANY


BGD plans to do a commercial development on a property. Relevant data
Asking price for the property is 300,000 dollars. Construction cost is 500,000 dollars. Selling price is approximated at 950,000 dollars. Variance application costs 30,000 dollars in fees and expenses
There is only 40% chance that the variance will be approved. 56

BILL GALLEN DEVELOPMENT COMPANY


A consultant can be hired for 5000 dollars. The consultant will provide an opinion about the approval of the application
P (Consultant predicts approval | approval granted) = 0.70 P (Consultant predicts denial | approval denied) = 0.80

BGD wishes to determine the optimal strategy

57

BILL GALLEN - Solution


Construction of the Decision Tree
Initially the company faces a decision about hiring the consultant. After this decision is made more decisions follow regarding
Application for the variance. Purchasing the option. Purchasing the property.
58

BILL GALLEN - The Decision Tree ing


t an t ul ns co 0 re t = hi s ot Co n
h not 0 Do Buy land Pu -300,000 rc ha -2 se 0, op 00 tio 0 n

0 3

Apply for variance -30,000

Do

Le to t u no s c Apply for variance Hi t h on re -30,000 co ire sid Co ns st ul a er ta = nt co th -5 00 ns e 0 ul de ta ci nt sio n


59

BILL GALLEN - The Decision Tree


Buy land and apply for variance ved ro pp .4 A De 0 nie d 0.6
ed ov r pp A 0.4 De nie d 0.6

120,000 -300000 30000 500000 + 950000 = Build Sell -500,000 950,000

Buy land -300,000

-70,000 -300000 30000 + 260000 = Sell 260,000 Build Sell -500,000 950,000 100,000

12

Purchase option and apply for

-50,000
60

BILL GALLEN - The Decision Tree


g othin Do n 0 Buy land -300,000 Pu rch -20 ase op ,00 tion 0
Buy land and apply for variance ed rov App .4 Apply for variance 0 Den -30,000 ied 0.6
ed rov App Apply12 variance0.4 for Den ied -30,000
0.6

Build -500,000

-300000 30000 500000 +950000 =120,000 Sell 950,000

Do

nt lta su on 0 ec hir st = t o no C

Buy land -300,000

-300000 30000 +260000 =-70,000 Sell 260,000 Build Sell -500,000 950,000 100,000

Hir ec o Co nsu lt st =- ant 50 00

Purchase option and apply for variance

-50,000
61

This is where we are at this stage


60

Let us consider the decision to hire a consultant


61

nt ulta s con e t hir no 0 Do

Done

Hi re

g hin t No Do

-5000

0. 4

co ns -5 00 ulta nt 0

t ic val d re pro P p A

Buy land -300,000 Pur cha se opt -20 ion ,00 0

Apply for variance -30,000 Apply for variance -30,000

Let us consider the decision to hire a consultant

BILL GALLEN The Decision Tree

ict ed l Pr nia De

ing Noth Do

-5000
Apply for variance -30,000

0.6

Buy land Pur-300,000 cha se opt -20 ion ,00 0

Apply for variance -30,000


62

BILL GALLEN - The Decision Tree


ed ov r pp A ? De nie d

Build -500,000

Sell 950,000

115,000

Co ns ul ta nt pr ed ict s

Sell 260,000

-75,000

an

ap

pr ov

al

63

BILL GALLEN - The Decision Tree


ed ov r pp A ? De nie d

Build -500,000

Sell 950,000

115,000

Sell 260,000

-75,000

The consultant serves as a source for additional information about denial or approval of the variance.
64

BILL GALLEN - The Decision Tree


ed ov r pp A ? De nie d

Build -500,000

Sell 950,000

115,000

Sell 260,000

-75,000

Therefore, at this point we need to calculate the posterior probabilities for the approval and denial of the variance application 65

BILL GALLEN - The Decision Tree


ed ov r pp A ? .7 De nie d

23

Build -500,000

24

Sell 950,000

115,000

25
-75,000

22

? .3

26

Sell 260,000

27

terior Probability of (approval | consultant predicts approval) = terior Probability of (denial | consultant predicts approval) = 0

The rest of the Decision Tree is built in a similar manner.

66

Determining the Optimal Strategy


Work backward from the end of each branch. At a state of nature node, calculate the expected value of the node. At a decision node, the branch that has the highest ending node value represents the optimal decision.
67

The Decision Tree

7 115,000 (0. 8050 115,000 ) 0 Build Sell 00 50 ,0 0 25 23 -500,000 24 15 500 950,000 1 08 ed ( 8 v pro 58,000Ap ? De 0.70 -22 22 -75,000 -75,000 -75,000 -75,000 nie -75,000 50 d 75,00 -75,000 (-7 - 0 22 0.30 Sell 5, 0 26 00 50 ? 27 260,000 0) 0 -2 (0 .3 250 )= 0 -2 25 00 With 58,000 as the chance node value,

BILL GALLEN - The Decision Tree Determining the Optimal 0 50 0 Strategy 115,000 115,000 115,000 =8 0 ) 115,000 115,000

we continue backward to evaluate the previous nodes.

68

$10,000 ot $20,000o n D ire h

BILL GALLEN - The Decision Tree Determining the Optimal $115,000 Strategy Build,
Sell
Ap pro ve d

$58,000

.7

Buy land; Apply l ova r H $20,000 for variance app ir ts ic e red P .4 Pr ed ict sd en $-5,000 .6 ial Do nothing

$-75,000
69

d nie De

.3
Sell land

BILL GALLEN - The Decision Tree Excel add-in: Tree Plan

70

BILL GALLEN - The Decision Tree Excel add-in: Tree Plan

71

6.7 Decision Making and Utility


Introduction
The expected value criterion may not be appropriate if the decision is a one-time opportunity with substantial risks. Decision makers do not always choose decisions based on the expected value criterion.
A lottery ticket has a negative net expected return. Insurance policies cost more than the present value of the expected loss the

72

The Utility Approach


It is assumed that a decision maker can rank decisions in a coherent manner. Utility values, U(V), reflect the decision makers perspective and attitude toward risk. Each payoff is assigned a utility value. Higher payoffs get larger utility value.

The optimal decision is the one that maximizes the expected utility.
73

Determining Utility Values


The technique provides an insightful look into the amount of risk the decision maker is willing to take. The concept is based on the decision makers preference to taking a sure payoff versus participating in a lottery.
74

Determining Utility Values


Indifference approach for assigning utility values List every possible payoff in the payoff table in ascending order. Assign a utility of 0 to the lowest value and a value of 1 to the highest value. For all other possible payoffs (Rij) ask the decision maker the following question:
75

Determining Utility Values


Indifference approach for assigning utility values Suppose you are given the option to select one of the following two alternatives:
Receive $Rij (one of the payoff values) for sure, Play a game of chance where you receive either
The highest payoff of $Rmax with probability p, or
76

Determining Utility Values


Indifference approach for assigning utility values

p 1-p Rij Rmin Rmax

What value of p would make you indifferent between the two situations? 77

Determining Utility Values


Indifference approach for assigning utility values

p 1-p Rij Rmin Rmax

The answer to this question is the indifference probability for the payoff Rij and is used as the utility

78

Determining Utility Values


Example:

Indifference approach for assigning utility values


s d d
1 2 1

150 -50

100 140

1 AlternativeFor p = 1.0, youll Alternative 2 prefer Alternative 2. A sure event (Game-of-chance) For p = 0.0, youll prefer Alternative 1. Thus, for some p $150 $100 between 0.0 and 1.0 1-p youll be indifferent p -50 between the alternatives. 79

Determining Utility Values


Indifference approach for assigning utility values
s d d
1 2 1

150 -50

100 140

Alternative 1 Lets assume Alternative 2 the A sure event (Game-of-chance) probability of indifference is p = .7. $150 $100 1-p U(100)=.7U(150)+ p -50 .3U(-50) 80 = .7(1) + .

Data

TOM BROWN - Determining Utility Values

Payoff Prob.

The highest payoff was $500. Lowest payoff was -$600. The indifference probabilities provided by Tom are
-600 -200 -150 -100 0 0 0.25 0.3 0.36 0.5 0.6 0.65 0.7 0.75 0.85 0.9

60 100 150 200 250 300 500 1

Tom wishes to determine his optimal investment Decision.

81

TOM BROWN Optimal decision (utility)


Utility Analysis Large Rise Small Rise No Change Small Fall Large Fall EU 0.36 0.65 0.75 0.9 0.5 0.632 0.85 0.75 0.7 0.36 0.3 0.671 1 0.85 0.65 0.25 0 0.675 0.6 0.6 0.6 0.6 0.6 0.6 0 0 0 0 0.2 0.3 0.3 0.1 0.1 Certain Payoff -600 -200 -150 -100 0 60 100 150 200 250 300 500 Utility 0 0.25 0.3 0.36 0.5 0.6 0.65 0.7 0.75 0.85 0.9 1

Gold Bond Stock C/D Account d5 d6 d7 d8 Probability

RESULTS Criteria Exp. Utility

Decision Stock

Value 0.675

82

Three types of Decision Makers


Risk Averse -Prefers a certain outcome to a chance outcome having the same expected value. Risk Taking - Prefers a chance outcome to a certain outcome having the same expected value. Risk Neutral - Is indifferent between a chance outcome and a certain outcome83

The Utility Curve for a Utility Risk Averse Decision Maker


U(200) U(150) EU(Game) U(100)
The utility of having $150 The utility of having $150 on hand on hand is larger than the is larger than the expected utility expected utility of a game whose expected of a game whose expected value value is also $150. is also $150.

100 0.5

150

200 0.5

Payoff

84

The Utility Curve for a Utility Risk Averse Decision Maker


U(200) U(150) EU(Game) U(100)
A risk averse decision maker avoids A risk averse decision maker avoids the thrill of a game-of-chance, the thrill of a game-of-chance, whose expected value is EV, if he whose expected value is EV, if he can have EV on hand for sure. can have EV on hand for sure. Furthermore, a risk Furthermore, a risk averse decision maker is averse decision maker is willing to pay a willing to pay a to buy himself (herself) to buy himself (herself) premium premium out of the out of the game-of-chance. game-of-chance.

100 0.5

CE 150

200 0.5

Payoff

85

Utility Risk Averse Decision Maker

isk R

al tr eu N

n io s ci De

er ak M

Risk Taking Decision Maker Payoff

86

6.8

Game Theory

Game theory can be used to determine optimal decisions in face of other decision making players. All the players are seeking to maximize their return. The payoff is based on the actions taken by all the decision making 87

Classification of Games
By number of players
Two players - Chess Multiplayer Poker

By total return
Zero Sum - the amount won and amount lost by all competitors are equal (Poker among friends) Nonzero Sum -the amount won and the amount lost by all competitors are not equal (Poker In A Casino)

By sequence of moves
Sequential - each player gets a play in a
88

IGA SUPERMARKET
The town of Gold Beach is served by two supermarkets: IGA and Sentry. Market share can be influenced by their advertising policies. The manager of each supermarket must decide weekly which area of operations to discount and emphasize in the stores newspaper flyer.
89

IGA SUPERMARKET
Data
The weekly percentage gain in market share for IGA, as a function of advertising emphasis. Sentry's Emphasis
IGA's M eat Em phasis Produce Grocery M eat Produce Grocery Bakery 2 2 -8 6 -2 0 6 -4 2 -7 1 -3

A gain in market share to IGA results in equivalent loss for Sentry, and vice90 versa (i.e. a zero sum game)

IGA needs to determine an advertising emphasis that will maximize its expected change in market share regardless of Sentrys action.
91

IGA SUPERMARKET - Solution


To prevent a sure loss of market share, both IGA and Sentry should select the weekly emphasis randomly. Thus, the question for both stores is: What proportion of the time each area should be emphasized by each store?
92

IGAs Linear Programming Model


Decision variables
X1 = the probability IGAs advertising focus is on meat. X2 = the probability IGAs advertising focus is on produce. X 3 = the probability IGAs advertising focus is on groceries.

Objective Function For IGA


Maximize expected market increase regardless of Sentrys advertising
93

IGAs Perspective
Constraints
IGAs market share increase for any given advertising focus selected by Sentry, must be at least V.

The model expected change IGAs in market share. Max V Sentrys S.T. advertising Meat 2X1 2X2 + 2X3 emphasis Produce 2X1 7 X3 V Groceries -8X1 6X2 + X3

V 94

Sentrys Linear Programming Model


Decision variables
Y1 = the probability Sentrys advertising

focus is on meat. Y2 = the probability Sentrys advertising focus is on produce. Y 3 = the probability Sentrys advertising focus is on groceries. Y4 = the probability Sentrys advertising focus is on bakery.

Objective Function For Sentry

95

Sentrys perspective
Constraints
Sentrys market share decrease for any given advertising focus selected by IGA, must not exceed V.

The Model

Min V S.T. 2Y1 V -2Y1 2Y1

+ 2Y2

8Y3

+ 6Y4

+ 6Y3 4Y4 V 7Y2 + Y3 3Y496

IGA SUPERMARKET Optimal Solution


For IGA
X1 = 0.3889; X2 = 0.5; X3 = 0.1111

For Sentry
Y1 = .3333; = .3333 Y2 = 0; Y3 = .3333; Y4

For both players V =0 (a fair game).


97

IGA Optimal Solution worksheet


Worksheet: [IGA.xls]Sheet1
Adjustable Cells
Cell $A$2 $B$2 $C$2 $D$2 Name X1 X2 X3 V Final Value 0.388888889 0.5 0.111111111 -6.75062E-29 Reduced Cost 0 0 0 0 Objective Allow able Allow able Coefficient Increase Decrease 0 4 6 0 4 2 0 1.5 2 1 1E+30 1

Constraints
Final Cell Name $E$4 $E$5 $E$6 $E$7 $E$8 Value R.H. Side Increase Decrease -1.11022E-16 -0.333333333 0 0 1E+30 6.75062E-29 0 0 0 1E+30 3.88578E-16 -0.333333333 0 1E+30 0 -2.77556E-16 -0.333333333 0 1E+30 0 1 0 1 0.000199941 1E+30

Shadow Price

Constraint Allow able Allow able

98

Copyright 2002 John Wiley & Sons, Inc. All rights reserved. Reproduction or translation of this work beyond that named in Section 117 of the United States Copyright Act without the express written consent of the copyright owner is unlawful. Requests for further information should be addressed to the Permissions Department, John Wiley & Sons, Inc. Adopters of the textbook are granted permission to make back-up copies for their own use only, to make copies for distribution to students of the course the textbook is used in, and to modify this material to best suit their instructional needs. Under no circumstances can copies be made for resale. The Publisher assumes no responsibility for errors, omissions, or damages, caused by the use of these programs or from the use of the information contained herein.

99