Download presentation

Presentation is loading. Please wait.

Published byTyrell Cauthorn Modified about 1 year ago

1
1 Spreadsheet Modeling & Decision Analysis: A Practical Introduction to Management Science, 3e by Cliff Ragsdale

2
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Decision Analysis Chapter 15

3
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Introduction to Decision Analysis u Models help managers gain insight and understanding, but they can’t make decisions. u Decision making often remains a difficult task due to: –uncertainty regarding the future –conflicting values or objectives u Consider the following example...

4
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Deciding Between Job Offers u Company A –In a new industry that could boom or bust. –Low starting salary, but could increase rapidly. –Located near friends, family and favorite sports team. u Company B –Established firm with financial strength and commitment to employees. –Higher starting salary but slower advancement opportunity. –Distant location, offering few cultural or sporting activities. u Which job would you take?

5
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Good Decisions vs. Good Outcomes u A structured approach to decision making can help us make good decisions, but can’t guarantee good outcomes. u Good decisions sometimes result in bad outcomes.

6
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Characteristics of Decision Problems u Alternatives - different courses of action intended to solve a problem. –Work for company A –Work for company B –Reject both offers and keep looking u Criteria - factors that are important to the decision maker and influenced by the alternatives. –Salary –Career potential –Location u States of Nature - future events not under the decision makers control. –Company A grows –Company A goes bust –etc

7
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning An Example: Magnolia Inns u Hartsfield International Airport in Atlanta, Georgia, is one of the busiest airports in the world. u It has expanded numerous times to accommodate increasing air traffic. u Commercial development around the airport prevents it from building additional runways to handle the future air traffic demands. u Plans are being developed to build another airport outside the city limits.

8
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning An Example: Magnolia Inns (con’t) u Two possible locations for the new airport have been identified, but a final decision is not expected to be made for another year. u The Magnolia Inns hotel chain intends to build a new facility near the new airport once its site is determined. u Land values around the two possible sites for the new airport are increasing as investors speculate that property values will increase greatly in the vicinity of the new airport. u See data in file Fig15-1.xls

9
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning The Decision Alternatives 1) Buy the parcel of land at location A. 2) Buy the parcel of land at location B. 3) Buy both parcels. 4) Buy nothing.

10
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning The Possible States of Nature 1) The new airport is built at location A. 2) The new airport is built at location B.

11
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Constructing a Payoff Matrix See file Fig15-1.xls

12
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Decision Rules u If the future state of nature (airport location) were known, it would be easy to make a decision. u Failing this, a variety of nonprobabilistic decision rules can be applied to this problem: –Maximax –Maximin –Minimax regret u No decision rule is always best and each has its own weaknesses.

13
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning The Maximax Decision Rule u Identify the maximum payoff for each alternative. u Choose the alternative with the largest maximum payoff. u See file Fig15-1.xls u Weakness –Consider the following payoff matrix State of Nature Decision 1 2 MAX A <--maximum B292929

14
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning The Maximin Decision Rule u Identify the minimum payoff for each alternative. u Choose the alternative with the largest minimum payoff. u See file Fig15-1.xls u Weakness –Consider the following payoff matrix State of Nature Decision 1 2 MIN A B <--maximum

15
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning The Minimax Regret Decision Rule u Compute the possible regret for each alternative under each state of nature. u Identify the maximum possible regret for each alternative. u Choose the alternative with the smallest maximum regret. u See file Fig15-1.xls

16
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Anomalies with the Minimax Regret Rule u Consider the following payoff matrix State of Nature Decision 1 2 A9 2 B46 State of Nature Decision 1 2 MAX A0 4 4 <--minimum B505 u The regret matrix is: u Note that we prefer A to B. u Now let’s add an alternative...

17
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Adding an Alternative u Consider the following payoff matrix State of Nature Decision 1 2 A9 2 B46 C39 State of Nature Decision 1 2 MAX A0 7 7 B535 <--minimum C606 u The regret matrix is: u Now we prefer B to A?

18
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Probabilistic Methods u Sometimes, the states of nature can be assigned probabilities that represent their likelihood of occurrence. u For decision problems that occur more than once, we can often estimate these probabilities from historical data. u Other decision problems (such as the Magnolia Inns problem) represent one-time decisions where historical data for estimating probabilities don’t exist. u In these cases, probabilities are often assigned subjectively based on interviews with one or more domain experts. u Highly structured interviewing techniques exist for soliciting probability estimates that are reasonably accurate and free of the unconscious biases that may impact an expert’s opinions. u We will focus on techniques that can be used once appropriate probability estimates have been obtained.

19
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Expected Monetary Value u Selects alternative with the largest expected monetary value (EMV) EMV i is the average payoff we’d receive if we faced the same decision problem numerous times and always selected alternative i. u See file Fig15-1.xls

20
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning EMV Caution u The EMV rule should be used with caution in one-time decision problems. u Weakness –Consider the following payoff matrix State of Nature Decision 1 2 EMV A15,000 -5,000 5,000 <--maximum B5,0004,0004,500 Probability0.50.5

21
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Expected Regret or Opportunity Loss u Selects alternative with the smallest expected regret or opportunity loss (EOL) u The decision with the largest EMV will also have the smallest EOL. u See file Fig15-1.xls

22
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning The Expected Value of Perfect Information u Suppose we could hire a consultant who could predict the future with 100% accuracy. u With such perfect information, Magnolia Inns’ average payoff would be: EV with PI = 0.4*$ *$11 = $11.8 (in millions) u Without perfect information, the EMV was $3.4 million. u The expected value of perfect information is therefore, EV of PI = $ $3.4 = $8.4 (in millions) u In general, EV of PI = EV with PI - maximum EMV u It will always be the case that, EV of PI = minimum EOL

23
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning A Decision Tree for Magnolia Inns Buy A -18 Buy B -12 Buy A&B -30 Buy nothing 0 Land Purchase Decision Airport Location A B A B B B A A Payoff

24
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Rolling Back A Decision Tree Buy A -18 Buy B -12 Buy A&B -30 Buy nothing 0 Land Purchase Decision Airport Location A B A B B B A A Payoff EMV=-2 EMV=3.4 EMV=1.4 EMV= 0 EMV=3.4

25
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Alternate Decision Tree Buy A -18 Buy B -12 Buy A&B -30 Buy nothing 0 Land Purchase Decision Airport Location A B A B B A Payoff EMV=-2 EMV=3.4 EMV=1.4 EMV=3.4 0

26
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Using TreePlan u TreePlan is an Excel add-in for decision trees. u See file Fig15-14.xls

27
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning About TreePlan u TreePlan is a shareware product developed by Dr. Mike Middleton at the University of San Francisco and distributed with this textbook at no charge to you. u If you like this software package and plan to use for more than 30 days, you are expected to pay a nominal registration fee. Details on registration are available near the end of the TreePlan help file.

28
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Multi-stage Decision Problems u Many problems involve a series of decisions u Example –Should you go out to dinner tonight? –If so, v How much will you spend? v Where will you go? v How will you get there? u Multi-stage decisions can be analyzed using decision trees

29
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Multi-Stage Decision Example: COM-TECH u Steve Hinton, owner of COM-TECH, is considering whether or not to apply for a $85,000 OSHA research grant for using wireless communications technology to enhance safety in the coal industry. u Steve would spend approximately $5,000 preparing the grant proposal and estimates a chance of actually receiving the grant. u If awarded the grant, Steve would then need to decide whether to use microwave, cellular, or infrared communications technology.

30
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning COM-TECH (continued) u Steve would need to acquire some new equipment depending on which technology is used. The cost of the equipment is summarized as: TechnologyEquipment Cost Microwave$4,000 Cellular$5,000 Infrared$4,000 u Steve knows he will also spend money in R&D, but he doesn’t know exactly what the R&D costs will be.

31
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning COM-TECH (continued) u Steve needs to synthesize all the factors in this problem to decide whether or not to submit a grant proposal to OSHA. u See file Fig15-26.xls Cost Prob.Cost Prob. Microwave$30, $60, Cellular$40, $70, Infrared$40, $80, Best Case Worst Case u Steve estimates the following best case and worst case R&D costs and probabilities, based on his expertise in each area.

32
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Analyzing Risk in a Decision Tree u How sensitive is the decision in the COM-TECH problem to changes in the probability estimates? u We can use Solver to determine the smallest probability of receiving the grant for which Steve should still be willing to submit the proposal. u Let’s go back to file Fig15-26.xls...

33
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Risk Profiles u A risk profile summarizes the make-up of an EMV. u The $13,500 EMV for COM-TECH was created as follows: Event Probability Payoff Receive grant, Low R&D costs0.5*0.9=0.45$36,000 Receive grant, High R&D costs0.5*0.1=0.05-$4,000 Don’t receive grant0.5-$5,000 EMV$13,500 u This can also be summarized in a decision tree. u See file Fig15-29.xls

34
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Using Sample Information in Decision Making u We can often obtain information about the possible outcomes of decisions before the decisions are made. u This sample information allows us to refine probability estimates associated with various outcomes.

35
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Example: Colonial Motors u Colonial Motors (CM) needs to determine whether to build a large or small plant for a new car it is developing. u The cost of constructing a large plant is $25 million and the cost of constructing a small plant is $15 million. u CM believes a 70% chance exists that demand for the new car will be high and a 30% chance that it will be low. u The payoffs (in millions of dollars) are summarized below. Demand Factory SizeHighLow Large$175 $95 Small$125$105 u See decision tree in file Fig15-32.xls

36
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Including Sample Information u Before making a decision, suppose CM conducts a consumer attitude survey (with zero cost). u The survey can indicate favorable or unfavorable attitudes toward the new car. Assume: P(favorable response) = 0.67 P(unfavorable response) = 0.33 u If the survey response is favorable, this should increase CM’s belief that demand will be high. Assume: P(high demand | favorable response)=0.9 P(low demand | favorable response)=0.1

37
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Including Sample Information (con’t) u If the survey response is unfavorable, this should increase CM’s belief that demand will be low. Assume: P(low demand | unfavorable response)=0.7 P(high demand | unfavorable response)=0.3 u See decision tree in file Fig15-33.xls

38
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning The Expected Value of Sample Information u How much should CM be willing to pay to conduct the consumer attitude survey? Expected Value of Sample Information Expected Value with Sample Information Expected Value without Sample Information = - u In the CM example, E.V. of Sample Info. = $ $126 = $0.82 million

39
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Computing Conditional Probabilities u Conditional probabilities (like those in the CM example) are often computed from joint probability tables. High Demand Low Demand Total Favorable Response Unfavorable Response Total u The joint probabilities indicate: u The marginal probabilities indicate:

40
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Computing Conditional Probabilities (cont’d) u In general, u So we have, High Low DemandDemand Total Favorable Response Unfavorable Response Total

41
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Bayes’s Theorem u Bayes’s Theorem provides another definition of conditional probability that is sometimes helpful. u For example,

42
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Utility Theory u Sometimes the decision with the highest EMV is not the most desired or most preferred alternative. u Consider the following payoff table, State of Nature Decision 1 2 EMV A150, ,000 60,000<--maximum B70,00040,00055,000 Probability u Decision makers have different attitudes toward risk: Some might prefer decision alternative A, Others would prefer decision alternative B. u Utility Theory incorporates risk preferences in the decision making process.

43
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Common Utility Functions Utility Payoff risk averse risk neutral risk seeking

44
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Constructing Utility Functions u Assign utility values of 0 to the worst payoff and 1 to the best. u For the previous example, U(-$30,000)=0 and U($150,000)=1 To find the utility associated with a $70,000 payoff identify the value p at which the decision maker is indifferent between: Alternative 1: Receive $70,000 with certainty. Alternative 2: Receive $150,000 with probability p and lose $30,000 with probability (1- p ).

45
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Constructing Utility Functions (cont’d) u If decision maker is indifferent when p=0.8: u U($70,000)=U($150,000)*0.8+U(-30,000)*0.2 =1*0.8+0*0.2=0.8 u When p=0.8, the expected value of Alternative 2 is: –$150,000*0.8 + $30,000*0.2 = $114,000 u The decision maker is risk averse. (Willing to accept $70,000 with certainty versus a risky situation with an expected value of $114,000.)

46
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Constructing Utility Functions (cont’d) u If we repeat this process with different values in Alternative 1, the decision maker’s utility function emerges (e.g., if U($40,000)=0.65):

47
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Comments u Certainty Equivalent -- the amount that is equivalent in the decision maker’s mind to a situation involving risk. (e.g., $70,000 was equivalent to Alternative 2 with p = 0.8) u Risk Premium -- the EMV the decision maker is willing to give up to avoid a risky decision. (e.g., Risk premium = $114,000-$70,000 = $44,000)

48
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Using Utilities to Make Decisions u Replace monetary values in payoff tables with utilities. u Consider the following utility table from the earlier example, State of NatureExpected Decision 1 2 Utility A B <--maximum Probability u Decision B provides the greatest utility even though it the payoff table indicated it had a smaller EMV.

49
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning x U(x) R =100 R =200 R=300 The Exponential Utility Function u The exponential utility function is often used to model classic risk averse behavior:

50
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Incorporating Utilities in TreePlan u TreePlan will automatically convert monetary values to utilities using the exponential utility function. First determine a value for the risk tolerance parameter R. R is equivalent to the maximum value of Y for which the decision maker is willing to accept the following gamble: Win $Y with probability 0.5, Lose $Y/2 with probability 0.5. Note that R must be expressed in the same units as the payoffs! In Excel, insert R in a cell named RT. (Note: RT must be outside the rectangular range containing the decision tree!) u On TreePlan’s ‘Options’ dialog box select, ‘Use Exponential Utility Function’ u See file Fig15-38.xls

51
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Multicriteria Decision Making u Decision problem often involve two or more conflicting criterion or objectives: –Investing: risk vs. return –Choosing Among Job Offers: salary, location, career potential, etc. –Selecting a Camcorder: price, warranty, zoom, weight, lighting, etc. –Choosing Among Job Applicants: education, experience, personality, etc. u We’ll consider two techniques for these types of problems: –The Multicriteria Scoring Model –The Analytic Hierarchy Process (AHP)

52
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning The Multicriteria Scoring Model u Score (or rate) each alternative on each criterion. u Assign weights the criterion reflecting their relative importance. For each alternative j, compute a weighted average score as: w i = weight for criterion i s ij = score for alternative i on criterion j u See file Fig15-41.xls

53
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning The Analytic Hierarchy Process (AHP) u Provides a structured approach for determining the scores and weights in a multicriteria scoring model. u We’ll illustrate AHP using the following example: –A company wants to purchase a new payroll and personnel records information system. –Three systems are being considered (X, Y and Z). –Three criteria are relevant: v Price v User support v Ease of use

54
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Pairwise Comparisons u The first step in AHP is to create a pairwise comparison matrix for each alternative on each criterion using the following values: Value Preference 1Equally Preferred 2Equally to Moderately Preferred 3Moderately Preferred 4Moderately to Strongly Preferred 5Strongly Preferred 6Strongly to Very Strongly Preferred 7Very Strongly Preferred 8 Very Strongly to Extremely eferred 9Extremely Preferred P ij = extent to which we prefer alternative i to j on a given criterion. We assume P ji = 1/P ij u See price comparisons in file Fig15-43.xls

55
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Normalization & Scoring u To normalize a pairwise comparison matrix, 1) Compute the sum of each column, 2) Divide each entry in the matrix by its column sum. The score (s j ) for each alternative is given by the average of each row in the normalized comparison matrix. u See file Fig15-43.xls

56
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Consistency u We can check to make sure the decision maker was consistent in making the comparisons. The consistency measure for alternative i is: where P ij = pairwise comparison of alternative i to j s j = score for alternative j If the decision maker was perfectly consistent, each C i should equal to the number of alternatives in the problem.

57
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Consistency (cont’d) u Typically, some inconsistency exists. u The inconsistency is not deemed a problem provided the Consistency Ratio (CR) is no more than 10% where, RI = for n =

58
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning Obtaining Remaining Scores & Weights u This process is repeated to obtain scores for the other criterion as well as the criterion weights. u The scores and weights are then used as inputs to a multicriteria scoring model in the usual way. u See file Fig15-43.xls

59
Spreadsheet Modeling and Decision Analysis, 3e, by Cliff Ragsdale. © 2001 South-Western/Thomson Learning End of Chapter 15

Similar presentations

© 2016 SlidePlayer.com Inc.

All rights reserved.

Ads by Google