Gregory S. Parnell, PhD, is a Professor of Practice in the Department of Industrial Engineering at the University of Arkansas in Fayetteville, AR. Terry A. Bresnick, MBA, is President of Innovative Decision Analysis, and Lecturer in the Department of Industrial Engineering at the University of Arkansas. Eric R. Johnson, PhD, is Director of Decision Science at GSK, where he supports drug development decision making. Steven N. Tani, PhD, is a retired Partner and Fellow of Strategic Decisions Group. Eric Specking, PhD, is a Principal Engineer for Infinity Labs and a Lecturer in the College of Engineering at the University of Arkansas in Fayetteville, AR.

• Foreword to the 1st Edition xviiForeword to the 2nd Edition xxiiiPreface xxviiAbout the Companion Website xxxi1 Introduction to Decision Analysis and Analytics 11.1 Introduction 11.2 Decision Analysis is a Social-Technical Process 31.3 Decision Analysis Applications 81.3.1 Oil and Gas Decision Analysis Success Story – Chevron 101.3.2 Pharmaceutical Decision Analysis Success Story – SmithKline Beecham 111.3.3 Military and Intelligence Decision Analysis Success Stories 111.4 Decision Analysis Practitioners and Professionals 121.4.1 Education and Training 121.4.2 Decision Analysis Professional Organizations 121.4.3 Problem Domain Professional Societies 131.4.4 Professional Service 131.5 Handbook Overview and Illustrative Examples 141.5.1 TechnoMagic New Product Launch 151.5.2 Geneptin Personalized Medicine for Breast Cancer 161.5.3 Data Center Location and IT Portfolio 171.5.4 Roughneck North American Strategy (RNAS) 171.6 Summary 17Key Terms 18References 182 Decision-Making Challenges 212.1 Introduction 222.2 Human Decision-Making 222.3 Decision-Making Challenges 232.4 Organizational Decision Processes 242.4.1 Culture 242.4.2 Impact of Stakeholders 252.4.3 Decision Level (Strategic, Tactical, Operational) 262.5 Credible Problem Domain Knowledge 282.5.1 Dispersion of Knowledge 282.5.2 Technical Knowledge – Essential for Credibility 282.5.3 Business Knowledge – Essential for Success 292.5.4 Role of Experts 292.5.5 Limitations of Experts 292.6 Behavioral Decision-Analysis Insights 292.6.1 Decision Traps and Barriers 302.6.2 Cognitive Biases 312.7 Two Anecdotes: Long-Term Success and a Temporary Success of Supporting the Human Decision-Making Process 342.8 Setting the Human Decision-making Context for the Illustrative Example Problems 352.8.1 TechnoMagic New Product Launch 362.8.2 Geneptin Personalized Medicine 362.8.3 Data Center Decision Problem 362.9 Summary 37Key Terms 37References 383 Foundations of Decision Analysis and Analytics 413.1 Introduction 413.2 Brief History of the Foundations of Decision Analysis 423.3 Five Rules – Theoretical Foundation of Decision Analysis 433.4 Scope of Decision Analysis 463.5 Decision Analysis and Data Analytics 473.6 Taxonomy of Decision Analysis Practice 493.6.1 Some DA Terminology 493.6.2 Taxonomy Division—Single or Multiple Objectives 503.6.2.1 Single-Objective Decision Analysis 503.6.2.2 Multiple-Objective Decision Analysis 513.6.3 Addressing Value Trade-Offs and Risk Preference Separately or Together? 523.6.4 Nonmonetary or Monetary Value Metric? 543.6.5 Degree of Simplicity in Multidimensional Value Function 543.7 Value-Focused Thinking 553.7.1 Four Major VFT Ideas 553.7.2 The Benefits of VFT 563.8 Summary 57Key Terms 57Acknowledgments 58References 584 Decision Analysis Soft Skills 614.1 Introduction 624.2 Thinking Strategically 624.3 Leading Decision Analysis Teams 634.4 Managing Decision Analysis Projects 644.5 Researching 654.6 Interviewing Individuals 654.6.1 Before the Interview 664.6.2 Schedule/Reschedule the Interview 674.6.3 During the Interview 674.6.4 After the Interview 674.7 Conducting Surveys 684.7.1 Preparing an Effective Survey: Determine the Goals, Survey Respondents, and Method for Collecting Survey Data 684.7.2 Executing a Survey Instrument: Developing the Survey Questions, Testing, and Distributing the Survey 694.8 Facilitating Groups 704.8.1 Facilitation Basics 704.8.2 Group Processes 724.8.2.1 Stages of Group Development 724.8.2.2 Planning 734.8.2.3 Pulsing 734.8.2.4 Pacing 734.8.3 Focus Groups 744.8.3.1 Preparing for the Focus Group Session 754.8.3.2 Executing the Focus Group Session 754.9 Aggregating across Experts 754.10 Communicating Analysis Insights 764.11 Summary 76Key Terms 77References 775 Use the Appropriate Decision Process 795.1 Introduction 795.2 What Is a Good Decision? 805.2.1 Decision Quality 805.2.2 The Six Elements of Decision Quality 805.2.3 Intuitive vs. Deliberative Decision-Making 815.2.4 Artificial Intelligence-Driven Decision-Making 825.3 Selecting the Appropriate Decision Process 835.3.1 Tailoring the Decision Process to the Decision 835.3.1.1 How Urgent Is the decision? 845.3.1.2 How Important Is the Decision? 845.3.1.3 Why Is This Decision Difficult to Make? 845.3.2 Two Best Practice Decision Processes 845.3.2.1 Dialogue Decision Process 845.3.2.2 Decision Conferencing 885.3.3 Two Flawed Decision Processes 885.3.3.1 Strictly Analytical Decision Processes 885.3.3.2 Advocacy Decision Processes 895.4 Decision Processes in Illustrative Examples 895.4.1 TechnoMagic New Product Launch 905.4.2 Geneptin Personalized Medicine 905.4.3 Data Center Location Decision 915.5 Organizational Decision Quality 915.6 Decision-Maker’s Bill of Rights 925.7 Summary 92Key Terms 93References 936 Frame the Decision Opportunity 956.1 Introduction 966.2 Declaring a Decision 966.3 What Is a Good Decision Frame? 976.4 Achieving a Good Decision Frame 986.4.1 Vision Statement 996.4.2 Issue Raising 1006.4.3 Categorization of Issues 1016.4.4 Decision Hierarchy 1016.4.5 Values and Trade-offs 1026.4.6 Initial Influence Diagram 1026.4.7 Decision Schedule and Logistics 1036.5 Using an Influence Diagram for Decision Framing 1036.5.1 Introduction to Influence Diagrams 1036.5.2 Influence Diagram Elements 1036.5.3 Influence Diagram Rules 1066.6 Framing the Decision Opportunities for the Illustrative Examples 1066.6.1 TechnoMagic New Product Launch 1066.6.2 Geneptin Personalized Medicine 1086.6.3 Data Center Decision 1096.7 Using Decision-Analysis Techniques to Frame Analytics Projects 1136.8 Summary 115Key Terms 115References 1167 Craft the Decision Objectives and Value Measures 1177.1 Introduction 1187.2 Shareholder and Stakeholder Value 1187.2.1 Private Company Example 1197.2.2 Government Agency Example 1197.3 Challenges in Identifying Objectives 1207.4 Identifying the Decision Objectives 1217.4.1 Questions to Help Identify Decision Objectives 1217.4.2 How to Get Answers to the Questions 1227.5 The Financial or Cost Objective 1237.5.1 Financial Objectives for Private Companies 1237.5.2 Cost Objective for Public Organizations 1237.6 Developing Value Measures 1247.7 Structuring Multiple Objectives 1247.7.1 Value Hierarchies 1257.7.2 Techniques for Developing Value Hierarchies 1277.7.3 Value Hierarchy Best Practices 1287.7.4 Cautions about Cost, Risk and -ilities Objectives 1287.8 Illustrative Examples 1307.8.1 TechnoMagic New Product Decision 1307.8.2 Geneptin 1307.8.3 Data Center Location 1307.9 Summary 132Key Terms 132References 1338 Design Creative Alternatives 1358.1 Introduction 1358.2 Characteristics of a Good Set of Alternatives 1368.3 Obstacles to Creating a Good Set of Alternatives 1378.4 The Expansive Phase of Creating Alternatives 1398.5 The Reductive Phase of Creating Alternatives 1408.6 Improving the Set of Alternatives 1438.7 Illustrative Examples 1438.7.1 TechnoMagic New Product Launch 1448.7.2 Geneptin Personalized Medicine 1448.7.3 Data Center Location 1458.8 Summary 146Key Terms 146References 1469 Perform Deterministic Analysis and Develop Insights 1499.1 Introduction 1499.2 Planning the Model Using Influence Diagrams 1519.3 Spreadsheet Software as the Modeling Platform 1529.3.1 Guidelines for Building a Spreadsheet Decision Model 1539.3.2 Scenario Analysis 1549.4 Deterministic Modeling with Net Present Value 1549.4.1 Net Present Value Calculation 1549.4.1.1 Explanation of NPV 1549.4.1.2 Simple NPV Example 1559.5 Two Illustrative NPV Examples 1569.5.1 TechnoMagic New Product Launch 1569.5.1.1 Control Panel Worksheet 1579.5.1.2 Calculations Worksheet 1599.5.1.3 Determining the Best Decisions Using Excel’s What If Analysis 1649.5.1.4 Additional Sensitivity Analysis 1659.5.2 Geneptin NPV Example 1689.6 Deterministic Modeling Using Multiple-Objective Decision Analysis 1709.6.1 The Additive Value Function 1709.6.2 Single-Dimensional Value Functions 1719.6.3 Swing Weights 1749.6.4 Swing Weight Matrix 1759.6.4.1 Consistency Rules 1769.6.4.2 Assessing Unnormalized Swing Weights 1769.6.4.3 Calculating Normalized Swing Weights 1779.6.4.4 Benefits of the Swing Weight Matrix 1779.6.5 Scoring the Alternatives 1779.6.6 Deterministic Analysis 1799.7 Illustrative MODA Problem – Data Center Location 1799.7.1 Additive Value Model 1799.7.2 Decision Analysis Software 1799.7.3 Value Functions 1809.7.4 Swing Weight Matrix 1809.7.5 Scoring the Alternatives 1829.7.6 Implementing the MODA Model in Excel 1829.7.6.1 Single-Dimensional Value Calculations 1859.7.6.2 Normalized Swing Weight Calculations 1859.7.6.3 Alternative Value Calculations 1859.7.6.4 Value Components 1859.7.6.5 Value Gaps 1899.7.6.6 Data Center Life Cycle Costs (LCCs) 1899.7.6.7 Value vs. Cost 1899.7.6.8 Waterfall Char 1919.7.6.9 Sensitivity Analysis 1939.7.6.10 Value-Focused Thinking 1949.8 Summary 194Key Terms 194References 19610 Quantify Uncertainty 19710.1 Introduction 19710.2 Use the Influence Diagram to Develop Probability Distributions 19810.3 Probability Assessment with Data 19910.3.1 General Process 19910.4 Elicit and Document Subject Matter Expert Assessments 20310.4.1 Heuristics and Biases 20310.4.2 Reference Events 20410.4.3 Assessment Protocol 20510.4.4 Assessing a Continuous Distribution 20710.4.5 The Reluctant Expert 20810.4.6 Making Assumptions to Inform Probabilistic Modeling 20910.5 Box Assessment Protocols with Artificial Intelligence Tools 21010.6 Illustrative Examples 21110.7 Summary 211Endnotes 211Key Terms 211References 21211 Perform Probabilistic Analysis and Identify Insights 21511.1 Introduction 21611.2 Exploration of Uncertainty: Simulation, Decision Trees, and Influence Diagrams 21611.2.1 Software for Simulation, Decision Trees, and Influence Diagrams 21711.2.2 Simulation 21711.2.3 TechnoMagic New Product Launch Monte Carlo Simulation 21811.2.4 Decision Trees 22411.2.4.1 Introduction 22411.2.4.2 Elements of a Decision Tree 22411.2.4.3 Solving a Decision Tree 22511.2.4.4 Product Launch Decision 22511.2.4.5 How to Solve a Decision Tree 22611.2.4.6 New Product Decision-Tree Solution 22611.2.4.7 One-Way Sensitivity Analysis 22611.2.4.8 Two-Way Sensitivity Analysis 22711.2.4.9 Limitations of Expected Value and Flaw of Averages 22711.2.4.10 Dominance 22911.2.5 Influence Diagrams 23011.2.5.1 Solving the Product Launch Decision with an Influence Diagram 23011.2.5.2 Converting the Influence Diagram to a Decision Tree 23311.2.5.3 Risk Profiles 23511.2.5.4 Comparison of Decision Trees and Influence Diagrams 23611.2.6 Choosing Between Monte Carlo Simulation and Decision Trees 23611.2.6.1 Downstream Decisions 23611.2.6.2 Number of Uncertainties 23711.2.6.3 Anomalies in the Value Function 23711.3 Value of Information and Value of Control 23811.3.1 Introduction 23811.3.2 Value of Information 23811.3.3 New Product Problem 23811.3.4 Perfect Information 23811.3.5 Expected Value of Control 24111.3.6 Imperfect Information 24111.3.7 Comparison of Information and Control 24111.4 Risk Attitude 24211.4.1 Delta Property 24311.4.2 Exponential Utility 24311.4.3 Assessing Risk Tolerance 24311.4.4 Calculating Certain Equivalents 24511.4.5 Evaluating “Small” Risks 24511.4.6 Going Beyond the Delta Property 24611.5 Illustrative Examples 24611.5.1 Geneptin Example 24611.5.2 Data Center 24711.6 Summary 248Key Terms 249References 25012 Portfolio Resource Allocation 25112.1 Introduction to Portfolio Decision Analysis 25112.2 Socio-technical Challenges with Portfolio Decision Analysis 25212.3 Portfolio Analysis Using Benefit–Cost Ratios 25312.4 Net Present Value Portfolio Analysis with Resource Constraints 25412.4.1 Characteristics of Portfolio Optimization 25412.4.2 Greedy Algorithm Using Profitability Index and the Efficient Frontier 25512.4.3 Application to Roughneck North American Strategy Portfolio 25812.4.4 Portfolio Risk Management 25912.4.5 Trading off Financial Goals with other Strategic Goals 25912.5 Multiobjective Portfolio Analysis with Resource Constraints 26012.5.1 IT Project Portfolio Problem 26012.5.2 Constraint Precision 26312.5.3 Integer Optimality 26312.6 Summary 264Key Terms 264References 26513 Communicate with Decision-Makers and Stakeholders 26713.1 Introduction 26713.2 Determining Communication Objectives 26913.3 Communicating with Senior Leaders 26913.4 Communicating Decision-Analysis Results 27313.4.1 Tell the Decision-Maker the Key Insights and Not the Details 27313.4.2 Communicating Quantitative Information 27413.4.3 Finding and Telling the Story 27513.4.4 Best Practices for Presenting Decision-Analysis Results 27713.4.5 Best Practices for Written Decision-Analysis Results 27913.5 Communicating Insights in the Illustrative Examples 28013.5.1 Roughneck North America Strategy 28013.5.2 Geneptin 28013.5.3 Data Center Location 28113.6 Summary 281Key Terms 282References 28214 Enable Decision Implementation 28514.1 Introduction 28514.2 Barriers to Involving Decision Implementers 28614.3 Involving Decision Implementers in the Decision Process 28714.4 Using Decision Analysis for Decision and Strategy Implementation 28914.4.1 Using the Decision Model for Decision Implementation 28914.4.2 Using Decision-Analysis Models to Support Decision Implementation 28914.4.2.1 Example 1: Gas Plant Implementation 28914.4.2.2 Example 2: Information Assurance Program Progress 29014.4.3 Using Decision Analysis to Assess Strategy Implementation 29114.4.3.1 Example 29214.5 Illustrative Examples 29214.5.1 Data Center 29214.5.2 Rnas 29314.6 Summary 293Key Term 293References 29315 Summary of Major Themes 29515.1 Overview 29615.2 Decision Analysis Helps Answer Important Decision-Making Questions 29615.3 The Purpose of Decision Analysis Is to Identify and Create Value for Shareholders and Stakeholders 29715.3.1 Single Objective Value 29815.3.2 Multiple Objective Value 29815.3.3 It Is Important to Distinguish Potential Value and Implemented Value 29815.4 Decision Analysis Is a Sociotechnical Process 29815.4.1 Social 29815.4.2 Technical 29815.5 Decision Analysts Need Decision-Making Knowledge and Soft Skills 29815.5.1 Decision Analysts Need to Understand Decision-Making Challenges 29915.5.2 Decision Analysts Must Develop Their Soft Skills 29915.6 The Decision-Analysis Process Must Be Tailored to the Decision and the Organization 30015.6.1 Decision Quality 30015.6.2 Decision Processes 30015.6.2.1 Decision Conferencing 30015.6.3 Dialogue Decision Process 30015.7 Decision Analysis Enables Data-Driven Decision-Making 30115.8 Decision Analysis Offers Powerful Analytic Tools to Support Decision-Making 30115.8.1 Decision Framing 30215.8.2 Identifying Objectives and Value Measures 30215.8.3 Developing Creative Alternatives 30215.8.4 Building Decision Models 30215.8.5 Performing Deterministic Analysis 30215.8.6 Identifying Uncertainties 30315.8.7 Performing Probabilistic Analysis 30315.8.8 Performing Portfolio Resource Allocation 30315.9 Conclusion 304Appendix A Probability Theory 305A. 1 Introduction 305A. 2 Distinctions and the Clairvoyance Test 305A. 3 Possibility Tree Representation of a Distinction 306A. 4 Probability as an Expression of Degree of Belief 307A. 5 Inferential Notation 307A. 6 Multiple Distinctions 307A. 7 Joint, Conditional, and Marginal Probabilities 307A.8 Calculating Joint Probabilities 308A.9 Dependent and Independent Probabilities 309A.10 Reversing Conditional Probabilities – Bayes’ Rule 310A.11 Probability Distributions 311A.11.1 Summary Statistics for a Probability Distribution 312A.12 Combining Uncertain Quantities 312References 313Appendix B Decision Conferencing 315B. 1 Introduction 315B. 2 Decision Conference Process and Format 317B. 3 Location, Facilities, and Equipment 317B. 4 Use of Group Processes 318B. 5 Advantages and Disadvantages 319B. 6 Best Practices 321B. 7 Summary 322Key Terms 322References 323Appendix C Resource Allocation with Incremental Benefit/Cost Analysis 325C. 1 Multiple Objective Portfolio Analysis with Resource Constraints 325C.. 1 Characteristics of Incremental Benefit/Cost Portfolio Analysis 325C.1. 2 Algorithm for Incremental Benefit/Cost Portfolio Analysis 326C..2. 1 Identify the Objective 326C.1.. 2 Generate Options 326C.1.2. 3 Assess Costs 328C.1.2. 4 Assess Benefits 329C.1.2. 5 Specify Constraints 330C.1.2. 6 Allocate Resources 331C.1.2. 7 Perform Sensitivity Analysis 332C.1. 3 Application to the Data Center Portfolio 332C.1. 4 Comparison with Portfolio Optimization 337C.1. 5 Strengths and Weaknesses of Incremental Benefit/Cost Portfolio Analysis 338C. 2 Summary 338Key Terms 339References 340Appendix D Roughneck North American Strategy 341D.1 Context 341D.2 Decision Process 342D.3 Framing 342D.4 Objectives and Value Measures 342D.5 Alternatives 344D.6 Uncertainty Structuring 344D.7 Uncertainty Quantification 347D.8 Evaluation Logic (Spreadsheet Model) 347D.8.1 Selectors 347D.8. 2 Inputs Sheet 348D.8. 3 Strategy Table Sheet 348D.8. 4 Calculations Sheets 348D. 9 Probabilistic Analysis 349D. 10 Real Options 355D. 11 Portfolio Resource Allocation 358Reference 360Index 361

Gregory S. Parnell, PhD, is a Professor of Practice in the Department of Industrial Engineering at the University of Arkansas in Fayetteville, AR. Terry A. Bresnick, MBA, is President of Innovative Decision Analysis, and Lecturer in the Department of Industrial Engineering at the University of Arkansas. Eric R. Johnson, PhD, is Director of Decision Science at GSK, where he supports drug development decision making. Steven N. Tani, PhD, is a retired Partner and Fellow of Strategic Decisions Group. Eric Specking, PhD, is a Principal Engineer for Infinity Labs and a Lecturer in the College of Engineering at the University of Arkansas in Fayetteville, AR.

• Foreword to the 1st Edition xviiForeword to the 2nd Edition xxiiiPreface xxviiAbout the Companion Website xxxi1 Introduction to Decision Analysis and Analytics 11.1 Introduction 11.2 Decision Analysis is a Social-Technical Process 31.3 Decision Analysis Applications 81.3.1 Oil and Gas Decision Analysis Success Story – Chevron 101.3.2 Pharmaceutical Decision Analysis Success Story – SmithKline Beecham 111.3.3 Military and Intelligence Decision Analysis Success Stories 111.4 Decision Analysis Practitioners and Professionals 121.4.1 Education and Training 121.4.2 Decision Analysis Professional Organizations 121.4.3 Problem Domain Professional Societies 131.4.4 Professional Service 131.5 Handbook Overview and Illustrative Examples 141.5.1 TechnoMagic New Product Launch 151.5.2 Geneptin Personalized Medicine for Breast Cancer 161.5.3 Data Center Location and IT Portfolio 171.5.4 Roughneck North American Strategy (RNAS) 171.6 Summary 17Key Terms 18References 182 Decision-Making Challenges 212.1 Introduction 222.2 Human Decision-Making 222.3 Decision-Making Challenges 232.4 Organizational Decision Processes 242.4.1 Culture 242.4.2 Impact of Stakeholders 252.4.3 Decision Level (Strategic, Tactical, Operational) 262.5 Credible Problem Domain Knowledge 282.5.1 Dispersion of Knowledge 282.5.2 Technical Knowledge – Essential for Credibility 282.5.3 Business Knowledge – Essential for Success 292.5.4 Role of Experts 292.5.5 Limitations of Experts 292.6 Behavioral Decision-Analysis Insights 292.6.1 Decision Traps and Barriers 302.6.2 Cognitive Biases 312.7 Two Anecdotes: Long-Term Success and a Temporary Success of Supporting the Human Decision-Making Process 342.8 Setting the Human Decision-making Context for the Illustrative Example Problems 352.8.1 TechnoMagic New Product Launch 362.8.2 Geneptin Personalized Medicine 362.8.3 Data Center Decision Problem 362.9 Summary 37Key Terms 37References 383 Foundations of Decision Analysis and Analytics 413.1 Introduction 413.2 Brief History of the Foundations of Decision Analysis 423.3 Five Rules – Theoretical Foundation of Decision Analysis 433.4 Scope of Decision Analysis 463.5 Decision Analysis and Data Analytics 473.6 Taxonomy of Decision Analysis Practice 493.6.1 Some DA Terminology 493.6.2 Taxonomy Division—Single or Multiple Objectives 503.6.2.1 Single-Objective Decision Analysis 503.6.2.2 Multiple-Objective Decision Analysis 513.6.3 Addressing Value Trade-Offs and Risk Preference Separately or Together? 523.6.4 Nonmonetary or Monetary Value Metric? 543.6.5 Degree of Simplicity in Multidimensional Value Function 543.7 Value-Focused Thinking 553.7.1 Four Major VFT Ideas 553.7.2 The Benefits of VFT 563.8 Summary 57Key Terms 57Acknowledgments 58References 584 Decision Analysis Soft Skills 614.1 Introduction 624.2 Thinking Strategically 624.3 Leading Decision Analysis Teams 634.4 Managing Decision Analysis Projects 644.5 Researching 654.6 Interviewing Individuals 654.6.1 Before the Interview 664.6.2 Schedule/Reschedule the Interview 674.6.3 During the Interview 674.6.4 After the Interview 674.7 Conducting Surveys 684.7.1 Preparing an Effective Survey: Determine the Goals, Survey Respondents, and Method for Collecting Survey Data 684.7.2 Executing a Survey Instrument: Developing the Survey Questions, Testing, and Distributing the Survey 694.8 Facilitating Groups 704.8.1 Facilitation Basics 704.8.2 Group Processes 724.8.2.1 Stages of Group Development 724.8.2.2 Planning 734.8.2.3 Pulsing 734.8.2.4 Pacing 734.8.3 Focus Groups 744.8.3.1 Preparing for the Focus Group Session 754.8.3.2 Executing the Focus Group Session 754.9 Aggregating across Experts 754.10 Communicating Analysis Insights 764.11 Summary 76Key Terms 77References 775 Use the Appropriate Decision Process 795.1 Introduction 795.2 What Is a Good Decision? 805.2.1 Decision Quality 805.2.2 The Six Elements of Decision Quality 805.2.3 Intuitive vs. Deliberative Decision-Making 815.2.4 Artificial Intelligence-Driven Decision-Making 825.3 Selecting the Appropriate Decision Process 835.3.1 Tailoring the Decision Process to the Decision 835.3.1.1 How Urgent Is the decision? 845.3.1.2 How Important Is the Decision? 845.3.1.3 Why Is This Decision Difficult to Make? 845.3.2 Two Best Practice Decision Processes 845.3.2.1 Dialogue Decision Process 845.3.2.2 Decision Conferencing 885.3.3 Two Flawed Decision Processes 885.3.3.1 Strictly Analytical Decision Processes 885.3.3.2 Advocacy Decision Processes 895.4 Decision Processes in Illustrative Examples 895.4.1 TechnoMagic New Product Launch 905.4.2 Geneptin Personalized Medicine 905.4.3 Data Center Location Decision 915.5 Organizational Decision Quality 915.6 Decision-Maker’s Bill of Rights 925.7 Summary 92Key Terms 93References 936 Frame the Decision Opportunity 956.1 Introduction 966.2 Declaring a Decision 966.3 What Is a Good Decision Frame? 976.4 Achieving a Good Decision Frame 986.4.1 Vision Statement 996.4.2 Issue Raising 1006.4.3 Categorization of Issues 1016.4.4 Decision Hierarchy 1016.4.5 Values and Trade-offs 1026.4.6 Initial Influence Diagram 1026.4.7 Decision Schedule and Logistics 1036.5 Using an Influence Diagram for Decision Framing 1036.5.1 Introduction to Influence Diagrams 1036.5.2 Influence Diagram Elements 1036.5.3 Influence Diagram Rules 1066.6 Framing the Decision Opportunities for the Illustrative Examples 1066.6.1 TechnoMagic New Product Launch 1066.6.2 Geneptin Personalized Medicine 1086.6.3 Data Center Decision 1096.7 Using Decision-Analysis Techniques to Frame Analytics Projects 1136.8 Summary 115Key Terms 115References 1167 Craft the Decision Objectives and Value Measures 1177.1 Introduction 1187.2 Shareholder and Stakeholder Value 1187.2.1 Private Company Example 1197.2.2 Government Agency Example 1197.3 Challenges in Identifying Objectives 1207.4 Identifying the Decision Objectives 1217.4.1 Questions to Help Identify Decision Objectives 1217.4.2 How to Get Answers to the Questions 1227.5 The Financial or Cost Objective 1237.5.1 Financial Objectives for Private Companies 1237.5.2 Cost Objective for Public Organizations 1237.6 Developing Value Measures 1247.7 Structuring Multiple Objectives 1247.7.1 Value Hierarchies 1257.7.2 Techniques for Developing Value Hierarchies 1277.7.3 Value Hierarchy Best Practices 1287.7.4 Cautions about Cost, Risk and -ilities Objectives 1287.8 Illustrative Examples 1307.8.1 TechnoMagic New Product Decision 1307.8.2 Geneptin 1307.8.3 Data Center Location 1307.9 Summary 132Key Terms 132References 1338 Design Creative Alternatives 1358.1 Introduction 1358.2 Characteristics of a Good Set of Alternatives 1368.3 Obstacles to Creating a Good Set of Alternatives 1378.4 The Expansive Phase of Creating Alternatives 1398.5 The Reductive Phase of Creating Alternatives 1408.6 Improving the Set of Alternatives 1438.7 Illustrative Examples 1438.7.1 TechnoMagic New Product Launch 1448.7.2 Geneptin Personalized Medicine 1448.7.3 Data Center Location 1458.8 Summary 146Key Terms 146References 1469 Perform Deterministic Analysis and Develop Insights 1499.1 Introduction 1499.2 Planning the Model Using Influence Diagrams 1519.3 Spreadsheet Software as the Modeling Platform 1529.3.1 Guidelines for Building a Spreadsheet Decision Model 1539.3.2 Scenario Analysis 1549.4 Deterministic Modeling with Net Present Value 1549.4.1 Net Present Value Calculation 1549.4.1.1 Explanation of NPV 1549.4.1.2 Simple NPV Example 1559.5 Two Illustrative NPV Examples 1569.5.1 TechnoMagic New Product Launch 1569.5.1.1 Control Panel Worksheet 1579.5.1.2 Calculations Worksheet 1599.5.1.3 Determining the Best Decisions Using Excel’s What If Analysis 1649.5.1.4 Additional Sensitivity Analysis 1659.5.2 Geneptin NPV Example 1689.6 Deterministic Modeling Using Multiple-Objective Decision Analysis 1709.6.1 The Additive Value Function 1709.6.2 Single-Dimensional Value Functions 1719.6.3 Swing Weights 1749.6.4 Swing Weight Matrix 1759.6.4.1 Consistency Rules 1769.6.4.2 Assessing Unnormalized Swing Weights 1769.6.4.3 Calculating Normalized Swing Weights 1779.6.4.4 Benefits of the Swing Weight Matrix 1779.6.5 Scoring the Alternatives 1779.6.6 Deterministic Analysis 1799.7 Illustrative MODA Problem – Data Center Location 1799.7.1 Additive Value Model 1799.7.2 Decision Analysis Software 1799.7.3 Value Functions 1809.7.4 Swing Weight Matrix 1809.7.5 Scoring the Alternatives 1829.7.6 Implementing the MODA Model in Excel 1829.7.6.1 Single-Dimensional Value Calculations 1859.7.6.2 Normalized Swing Weight Calculations 1859.7.6.3 Alternative Value Calculations 1859.7.6.4 Value Components 1859.7.6.5 Value Gaps 1899.7.6.6 Data Center Life Cycle Costs (LCCs) 1899.7.6.7 Value vs. Cost 1899.7.6.8 Waterfall Char 1919.7.6.9 Sensitivity Analysis 1939.7.6.10 Value-Focused Thinking 1949.8 Summary 194Key Terms 194References 19610 Quantify Uncertainty 19710.1 Introduction 19710.2 Use the Influence Diagram to Develop Probability Distributions 19810.3 Probability Assessment with Data 19910.3.1 General Process 19910.4 Elicit and Document Subject Matter Expert Assessments 20310.4.1 Heuristics and Biases 20310.4.2 Reference Events 20410.4.3 Assessment Protocol 20510.4.4 Assessing a Continuous Distribution 20710.4.5 The Reluctant Expert 20810.4.6 Making Assumptions to Inform Probabilistic Modeling 20910.5 Box Assessment Protocols with Artificial Intelligence Tools 21010.6 Illustrative Examples 21110.7 Summary 211Endnotes 211Key Terms 211References 21211 Perform Probabilistic Analysis and Identify Insights 21511.1 Introduction 21611.2 Exploration of Uncertainty: Simulation, Decision Trees, and Influence Diagrams 21611.2.1 Software for Simulation, Decision Trees, and Influence Diagrams 21711.2.2 Simulation 21711.2.3 TechnoMagic New Product Launch Monte Carlo Simulation 21811.2.4 Decision Trees 22411.2.4.1 Introduction 22411.2.4.2 Elements of a Decision Tree 22411.2.4.3 Solving a Decision Tree 22511.2.4.4 Product Launch Decision 22511.2.4.5 How to Solve a Decision Tree 22611.2.4.6 New Product Decision-Tree Solution 22611.2.4.7 One-Way Sensitivity Analysis 22611.2.4.8 Two-Way Sensitivity Analysis 22711.2.4.9 Limitations of Expected Value and Flaw of Averages 22711.2.4.10 Dominance 22911.2.5 Influence Diagrams 23011.2.5.1 Solving the Product Launch Decision with an Influence Diagram 23011.2.5.2 Converting the Influence Diagram to a Decision Tree 23311.2.5.3 Risk Profiles 23511.2.5.4 Comparison of Decision Trees and Influence Diagrams 23611.2.6 Choosing Between Monte Carlo Simulation and Decision Trees 23611.2.6.1 Downstream Decisions 23611.2.6.2 Number of Uncertainties 23711.2.6.3 Anomalies in the Value Function 23711.3 Value of Information and Value of Control 23811.3.1 Introduction 23811.3.2 Value of Information 23811.3.3 New Product Problem 23811.3.4 Perfect Information 23811.3.5 Expected Value of Control 24111.3.6 Imperfect Information 24111.3.7 Comparison of Information and Control 24111.4 Risk Attitude 24211.4.1 Delta Property 24311.4.2 Exponential Utility 24311.4.3 Assessing Risk Tolerance 24311.4.4 Calculating Certain Equivalents 24511.4.5 Evaluating “Small” Risks 24511.4.6 Going Beyond the Delta Property 24611.5 Illustrative Examples 24611.5.1 Geneptin Example 24611.5.2 Data Center 24711.6 Summary 248Key Terms 249References 25012 Portfolio Resource Allocation 25112.1 Introduction to Portfolio Decision Analysis 25112.2 Socio-technical Challenges with Portfolio Decision Analysis 25212.3 Portfolio Analysis Using Benefit–Cost Ratios 25312.4 Net Present Value Portfolio Analysis with Resource Constraints 25412.4.1 Characteristics of Portfolio Optimization 25412.4.2 Greedy Algorithm Using Profitability Index and the Efficient Frontier 25512.4.3 Application to Roughneck North American Strategy Portfolio 25812.4.4 Portfolio Risk Management 25912.4.5 Trading off Financial Goals with other Strategic Goals 25912.5 Multiobjective Portfolio Analysis with Resource Constraints 26012.5.1 IT Project Portfolio Problem 26012.5.2 Constraint Precision 26312.5.3 Integer Optimality 26312.6 Summary 264Key Terms 264References 26513 Communicate with Decision-Makers and Stakeholders 26713.1 Introduction 26713.2 Determining Communication Objectives 26913.3 Communicating with Senior Leaders 26913.4 Communicating Decision-Analysis Results 27313.4.1 Tell the Decision-Maker the Key Insights and Not the Details 27313.4.2 Communicating Quantitative Information 27413.4.3 Finding and Telling the Story 27513.4.4 Best Practices for Presenting Decision-Analysis Results 27713.4.5 Best Practices for Written Decision-Analysis Results 27913.5 Communicating Insights in the Illustrative Examples 28013.5.1 Roughneck North America Strategy 28013.5.2 Geneptin 28013.5.3 Data Center Location 28113.6 Summary 281Key Terms 282References 28214 Enable Decision Implementation 28514.1 Introduction 28514.2 Barriers to Involving Decision Implementers 28614.3 Involving Decision Implementers in the Decision Process 28714.4 Using Decision Analysis for Decision and Strategy Implementation 28914.4.1 Using the Decision Model for Decision Implementation 28914.4.2 Using Decision-Analysis Models to Support Decision Implementation 28914.4.2.1 Example 1: Gas Plant Implementation 28914.4.2.2 Example 2: Information Assurance Program Progress 29014.4.3 Using Decision Analysis to Assess Strategy Implementation 29114.4.3.1 Example 29214.5 Illustrative Examples 29214.5.1 Data Center 29214.5.2 Rnas 29314.6 Summary 293Key Term 293References 29315 Summary of Major Themes 29515.1 Overview 29615.2 Decision Analysis Helps Answer Important Decision-Making Questions 29615.3 The Purpose of Decision Analysis Is to Identify and Create Value for Shareholders and Stakeholders 29715.3.1 Single Objective Value 29815.3.2 Multiple Objective Value 29815.3.3 It Is Important to Distinguish Potential Value and Implemented Value 29815.4 Decision Analysis Is a Sociotechnical Process 29815.4.1 Social 29815.4.2 Technical 29815.5 Decision Analysts Need Decision-Making Knowledge and Soft Skills 29815.5.1 Decision Analysts Need to Understand Decision-Making Challenges 29915.5.2 Decision Analysts Must Develop Their Soft Skills 29915.6 The Decision-Analysis Process Must Be Tailored to the Decision and the Organization 30015.6.1 Decision Quality 30015.6.2 Decision Processes 30015.6.2.1 Decision Conferencing 30015.6.3 Dialogue Decision Process 30015.7 Decision Analysis Enables Data-Driven Decision-Making 30115.8 Decision Analysis Offers Powerful Analytic Tools to Support Decision-Making 30115.8.1 Decision Framing 30215.8.2 Identifying Objectives and Value Measures 30215.8.3 Developing Creative Alternatives 30215.8.4 Building Decision Models 30215.8.5 Performing Deterministic Analysis 30215.8.6 Identifying Uncertainties 30315.8.7 Performing Probabilistic Analysis 30315.8.8 Performing Portfolio Resource Allocation 30315.9 Conclusion 304Appendix A Probability Theory 305A. 1 Introduction 305A. 2 Distinctions and the Clairvoyance Test 305A. 3 Possibility Tree Representation of a Distinction 306A. 4 Probability as an Expression of Degree of Belief 307A. 5 Inferential Notation 307A. 6 Multiple Distinctions 307A. 7 Joint, Conditional, and Marginal Probabilities 307A.8 Calculating Joint Probabilities 308A.9 Dependent and Independent Probabilities 309A.10 Reversing Conditional Probabilities – Bayes’ Rule 310A.11 Probability Distributions 311A.11.1 Summary Statistics for a Probability Distribution 312A.12 Combining Uncertain Quantities 312References 313Appendix B Decision Conferencing 315B. 1 Introduction 315B. 2 Decision Conference Process and Format 317B. 3 Location, Facilities, and Equipment 317B. 4 Use of Group Processes 318B. 5 Advantages and Disadvantages 319B. 6 Best Practices 321B. 7 Summary 322Key Terms 322References 323Appendix C Resource Allocation with Incremental Benefit/Cost Analysis 325C. 1 Multiple Objective Portfolio Analysis with Resource Constraints 325C.. 1 Characteristics of Incremental Benefit/Cost Portfolio Analysis 325C.1. 2 Algorithm for Incremental Benefit/Cost Portfolio Analysis 326C..2. 1 Identify the Objective 326C.1.. 2 Generate Options 326C.1.2. 3 Assess Costs 328C.1.2. 4 Assess Benefits 329C.1.2. 5 Specify Constraints 330C.1.2. 6 Allocate Resources 331C.1.2. 7 Perform Sensitivity Analysis 332C.1. 3 Application to the Data Center Portfolio 332C.1. 4 Comparison with Portfolio Optimization 337C.1. 5 Strengths and Weaknesses of Incremental Benefit/Cost Portfolio Analysis 338C. 2 Summary 338Key Terms 339References 340Appendix D Roughneck North American Strategy 341D.1 Context 341D.2 Decision Process 342D.3 Framing 342D.4 Objectives and Value Measures 342D.5 Alternatives 344D.6 Uncertainty Structuring 344D.7 Uncertainty Quantification 347D.8 Evaluation Logic (Spreadsheet Model) 347D.8.1 Selectors 347D.8. 2 Inputs Sheet 348D.8. 3 Strategy Table Sheet 348D.8. 4 Calculations Sheets 348D. 9 Probabilistic Analysis 349D. 10 Real Options 355D. 11 Portfolio Resource Allocation 358Reference 360Index 361

Gregory S. Parnell, PhD, is a Professor of Practice in the Department of Industrial Engineering at the University of Arkansas in Fayetteville, AR. Terry A. Bresnick, MBA, is President of Innovative Decision Analysis, and Lecturer in the Department of Industrial Engineering at the University of Arkansas. Eric R. Johnson, PhD, is Director of Decision Science at GSK, where he supports drug development decision making. Steven N. Tani, PhD, is a retired Partner and Fellow of Strategic Decisions Group. Eric Specking, PhD, is a Principal Engineer for Infinity Labs and a Lecturer in the College of Engineering at the University of Arkansas in Fayetteville, AR.

• Foreword to the 1st Edition xviiForeword to the 2nd Edition xxiiiPreface xxviiAbout the Companion Website xxxi1 Introduction to Decision Analysis and Analytics 11.1 Introduction 11.2 Decision Analysis is a Social-Technical Process 31.3 Decision Analysis Applications 81.3.1 Oil and Gas Decision Analysis Success Story – Chevron 101.3.2 Pharmaceutical Decision Analysis Success Story – SmithKline Beecham 111.3.3 Military and Intelligence Decision Analysis Success Stories 111.4 Decision Analysis Practitioners and Professionals 121.4.1 Education and Training 121.4.2 Decision Analysis Professional Organizations 121.4.3 Problem Domain Professional Societies 131.4.4 Professional Service 131.5 Handbook Overview and Illustrative Examples 141.5.1 TechnoMagic New Product Launch 151.5.2 Geneptin Personalized Medicine for Breast Cancer 161.5.3 Data Center Location and IT Portfolio 171.5.4 Roughneck North American Strategy (RNAS) 171.6 Summary 17Key Terms 18References 182 Decision-Making Challenges 212.1 Introduction 222.2 Human Decision-Making 222.3 Decision-Making Challenges 232.4 Organizational Decision Processes 242.4.1 Culture 242.4.2 Impact of Stakeholders 252.4.3 Decision Level (Strategic, Tactical, Operational) 262.5 Credible Problem Domain Knowledge 282.5.1 Dispersion of Knowledge 282.5.2 Technical Knowledge – Essential for Credibility 282.5.3 Business Knowledge – Essential for Success 292.5.4 Role of Experts 292.5.5 Limitations of Experts 292.6 Behavioral Decision-Analysis Insights 292.6.1 Decision Traps and Barriers 302.6.2 Cognitive Biases 312.7 Two Anecdotes: Long-Term Success and a Temporary Success of Supporting the Human Decision-Making Process 342.8 Setting the Human Decision-making Context for the Illustrative Example Problems 352.8.1 TechnoMagic New Product Launch 362.8.2 Geneptin Personalized Medicine 362.8.3 Data Center Decision Problem 362.9 Summary 37Key Terms 37References 383 Foundations of Decision Analysis and Analytics 413.1 Introduction 413.2 Brief History of the Foundations of Decision Analysis 423.3 Five Rules – Theoretical Foundation of Decision Analysis 433.4 Scope of Decision Analysis 463.5 Decision Analysis and Data Analytics 473.6 Taxonomy of Decision Analysis Practice 493.6.1 Some DA Terminology 493.6.2 Taxonomy Division—Single or Multiple Objectives 503.6.2.1 Single-Objective Decision Analysis 503.6.2.2 Multiple-Objective Decision Analysis 513.6.3 Addressing Value Trade-Offs and Risk Preference Separately or Together? 523.6.4 Nonmonetary or Monetary Value Metric? 543.6.5 Degree of Simplicity in Multidimensional Value Function 543.7 Value-Focused Thinking 553.7.1 Four Major VFT Ideas 553.7.2 The Benefits of VFT 563.8 Summary 57Key Terms 57Acknowledgments 58References 584 Decision Analysis Soft Skills 614.1 Introduction 624.2 Thinking Strategically 624.3 Leading Decision Analysis Teams 634.4 Managing Decision Analysis Projects 644.5 Researching 654.6 Interviewing Individuals 654.6.1 Before the Interview 664.6.2 Schedule/Reschedule the Interview 674.6.3 During the Interview 674.6.4 After the Interview 674.7 Conducting Surveys 684.7.1 Preparing an Effective Survey: Determine the Goals, Survey Respondents, and Method for Collecting Survey Data 684.7.2 Executing a Survey Instrument: Developing the Survey Questions, Testing, and Distributing the Survey 694.8 Facilitating Groups 704.8.1 Facilitation Basics 704.8.2 Group Processes 724.8.2.1 Stages of Group Development 724.8.2.2 Planning 734.8.2.3 Pulsing 734.8.2.4 Pacing 734.8.3 Focus Groups 744.8.3.1 Preparing for the Focus Group Session 754.8.3.2 Executing the Focus Group Session 754.9 Aggregating across Experts 754.10 Communicating Analysis Insights 764.11 Summary 76Key Terms 77References 775 Use the Appropriate Decision Process 795.1 Introduction 795.2 What Is a Good Decision? 805.2.1 Decision Quality 805.2.2 The Six Elements of Decision Quality 805.2.3 Intuitive vs. Deliberative Decision-Making 815.2.4 Artificial Intelligence-Driven Decision-Making 825.3 Selecting the Appropriate Decision Process 835.3.1 Tailoring the Decision Process to the Decision 835.3.1.1 How Urgent Is the decision? 845.3.1.2 How Important Is the Decision? 845.3.1.3 Why Is This Decision Difficult to Make? 845.3.2 Two Best Practice Decision Processes 845.3.2.1 Dialogue Decision Process 845.3.2.2 Decision Conferencing 885.3.3 Two Flawed Decision Processes 885.3.3.1 Strictly Analytical Decision Processes 885.3.3.2 Advocacy Decision Processes 895.4 Decision Processes in Illustrative Examples 895.4.1 TechnoMagic New Product Launch 905.4.2 Geneptin Personalized Medicine 905.4.3 Data Center Location Decision 915.5 Organizational Decision Quality 915.6 Decision-Maker’s Bill of Rights 925.7 Summary 92Key Terms 93References 936 Frame the Decision Opportunity 956.1 Introduction 966.2 Declaring a Decision 966.3 What Is a Good Decision Frame? 976.4 Achieving a Good Decision Frame 986.4.1 Vision Statement 996.4.2 Issue Raising 1006.4.3 Categorization of Issues 1016.4.4 Decision Hierarchy 1016.4.5 Values and Trade-offs 1026.4.6 Initial Influence Diagram 1026.4.7 Decision Schedule and Logistics 1036.5 Using an Influence Diagram for Decision Framing 1036.5.1 Introduction to Influence Diagrams 1036.5.2 Influence Diagram Elements 1036.5.3 Influence Diagram Rules 1066.6 Framing the Decision Opportunities for the Illustrative Examples 1066.6.1 TechnoMagic New Product Launch 1066.6.2 Geneptin Personalized Medicine 1086.6.3 Data Center Decision 1096.7 Using Decision-Analysis Techniques to Frame Analytics Projects 1136.8 Summary 115Key Terms 115References 1167 Craft the Decision Objectives and Value Measures 1177.1 Introduction 1187.2 Shareholder and Stakeholder Value 1187.2.1 Private Company Example 1197.2.2 Government Agency Example 1197.3 Challenges in Identifying Objectives 1207.4 Identifying the Decision Objectives 1217.4.1 Questions to Help Identify Decision Objectives 1217.4.2 How to Get Answers to the Questions 1227.5 The Financial or Cost Objective 1237.5.1 Financial Objectives for Private Companies 1237.5.2 Cost Objective for Public Organizations 1237.6 Developing Value Measures 1247.7 Structuring Multiple Objectives 1247.7.1 Value Hierarchies 1257.7.2 Techniques for Developing Value Hierarchies 1277.7.3 Value Hierarchy Best Practices 1287.7.4 Cautions about Cost, Risk and -ilities Objectives 1287.8 Illustrative Examples 1307.8.1 TechnoMagic New Product Decision 1307.8.2 Geneptin 1307.8.3 Data Center Location 1307.9 Summary 132Key Terms 132References 1338 Design Creative Alternatives 1358.1 Introduction 1358.2 Characteristics of a Good Set of Alternatives 1368.3 Obstacles to Creating a Good Set of Alternatives 1378.4 The Expansive Phase of Creating Alternatives 1398.5 The Reductive Phase of Creating Alternatives 1408.6 Improving the Set of Alternatives 1438.7 Illustrative Examples 1438.7.1 TechnoMagic New Product Launch 1448.7.2 Geneptin Personalized Medicine 1448.7.3 Data Center Location 1458.8 Summary 146Key Terms 146References 1469 Perform Deterministic Analysis and Develop Insights 1499.1 Introduction 1499.2 Planning the Model Using Influence Diagrams 1519.3 Spreadsheet Software as the Modeling Platform 1529.3.1 Guidelines for Building a Spreadsheet Decision Model 1539.3.2 Scenario Analysis 1549.4 Deterministic Modeling with Net Present Value 1549.4.1 Net Present Value Calculation 1549.4.1.1 Explanation of NPV 1549.4.1.2 Simple NPV Example 1559.5 Two Illustrative NPV Examples 1569.5.1 TechnoMagic New Product Launch 1569.5.1.1 Control Panel Worksheet 1579.5.1.2 Calculations Worksheet 1599.5.1.3 Determining the Best Decisions Using Excel’s What If Analysis 1649.5.1.4 Additional Sensitivity Analysis 1659.5.2 Geneptin NPV Example 1689.6 Deterministic Modeling Using Multiple-Objective Decision Analysis 1709.6.1 The Additive Value Function 1709.6.2 Single-Dimensional Value Functions 1719.6.3 Swing Weights 1749.6.4 Swing Weight Matrix 1759.6.4.1 Consistency Rules 1769.6.4.2 Assessing Unnormalized Swing Weights 1769.6.4.3 Calculating Normalized Swing Weights 1779.6.4.4 Benefits of the Swing Weight Matrix 1779.6.5 Scoring the Alternatives 1779.6.6 Deterministic Analysis 1799.7 Illustrative MODA Problem – Data Center Location 1799.7.1 Additive Value Model 1799.7.2 Decision Analysis Software 1799.7.3 Value Functions 1809.7.4 Swing Weight Matrix 1809.7.5 Scoring the Alternatives 1829.7.6 Implementing the MODA Model in Excel 1829.7.6.1 Single-Dimensional Value Calculations 1859.7.6.2 Normalized Swing Weight Calculations 1859.7.6.3 Alternative Value Calculations 1859.7.6.4 Value Components 1859.7.6.5 Value Gaps 1899.7.6.6 Data Center Life Cycle Costs (LCCs) 1899.7.6.7 Value vs. Cost 1899.7.6.8 Waterfall Char 1919.7.6.9 Sensitivity Analysis 1939.7.6.10 Value-Focused Thinking 1949.8 Summary 194Key Terms 194References 19610 Quantify Uncertainty 19710.1 Introduction 19710.2 Use the Influence Diagram to Develop Probability Distributions 19810.3 Probability Assessment with Data 19910.3.1 General Process 19910.4 Elicit and Document Subject Matter Expert Assessments 20310.4.1 Heuristics and Biases 20310.4.2 Reference Events 20410.4.3 Assessment Protocol 20510.4.4 Assessing a Continuous Distribution 20710.4.5 The Reluctant Expert 20810.4.6 Making Assumptions to Inform Probabilistic Modeling 20910.5 Box Assessment Protocols with Artificial Intelligence Tools 21010.6 Illustrative Examples 21110.7 Summary 211Endnotes 211Key Terms 211References 21211 Perform Probabilistic Analysis and Identify Insights 21511.1 Introduction 21611.2 Exploration of Uncertainty: Simulation, Decision Trees, and Influence Diagrams 21611.2.1 Software for Simulation, Decision Trees, and Influence Diagrams 21711.2.2 Simulation 21711.2.3 TechnoMagic New Product Launch Monte Carlo Simulation 21811.2.4 Decision Trees 22411.2.4.1 Introduction 22411.2.4.2 Elements of a Decision Tree 22411.2.4.3 Solving a Decision Tree 22511.2.4.4 Product Launch Decision 22511.2.4.5 How to Solve a Decision Tree 22611.2.4.6 New Product Decision-Tree Solution 22611.2.4.7 One-Way Sensitivity Analysis 22611.2.4.8 Two-Way Sensitivity Analysis 22711.2.4.9 Limitations of Expected Value and Flaw of Averages 22711.2.4.10 Dominance 22911.2.5 Influence Diagrams 23011.2.5.1 Solving the Product Launch Decision with an Influence Diagram 23011.2.5.2 Converting the Influence Diagram to a Decision Tree 23311.2.5.3 Risk Profiles 23511.2.5.4 Comparison of Decision Trees and Influence Diagrams 23611.2.6 Choosing Between Monte Carlo Simulation and Decision Trees 23611.2.6.1 Downstream Decisions 23611.2.6.2 Number of Uncertainties 23711.2.6.3 Anomalies in the Value Function 23711.3 Value of Information and Value of Control 23811.3.1 Introduction 23811.3.2 Value of Information 23811.3.3 New Product Problem 23811.3.4 Perfect Information 23811.3.5 Expected Value of Control 24111.3.6 Imperfect Information 24111.3.7 Comparison of Information and Control 24111.4 Risk Attitude 24211.4.1 Delta Property 24311.4.2 Exponential Utility 24311.4.3 Assessing Risk Tolerance 24311.4.4 Calculating Certain Equivalents 24511.4.5 Evaluating “Small” Risks 24511.4.6 Going Beyond the Delta Property 24611.5 Illustrative Examples 24611.5.1 Geneptin Example 24611.5.2 Data Center 24711.6 Summary 248Key Terms 249References 25012 Portfolio Resource Allocation 25112.1 Introduction to Portfolio Decision Analysis 25112.2 Socio-technical Challenges with Portfolio Decision Analysis 25212.3 Portfolio Analysis Using Benefit–Cost Ratios 25312.4 Net Present Value Portfolio Analysis with Resource Constraints 25412.4.1 Characteristics of Portfolio Optimization 25412.4.2 Greedy Algorithm Using Profitability Index and the Efficient Frontier 25512.4.3 Application to Roughneck North American Strategy Portfolio 25812.4.4 Portfolio Risk Management 25912.4.5 Trading off Financial Goals with other Strategic Goals 25912.5 Multiobjective Portfolio Analysis with Resource Constraints 26012.5.1 IT Project Portfolio Problem 26012.5.2 Constraint Precision 26312.5.3 Integer Optimality 26312.6 Summary 264Key Terms 264References 26513 Communicate with Decision-Makers and Stakeholders 26713.1 Introduction 26713.2 Determining Communication Objectives 26913.3 Communicating with Senior Leaders 26913.4 Communicating Decision-Analysis Results 27313.4.1 Tell the Decision-Maker the Key Insights and Not the Details 27313.4.2 Communicating Quantitative Information 27413.4.3 Finding and Telling the Story 27513.4.4 Best Practices for Presenting Decision-Analysis Results 27713.4.5 Best Practices for Written Decision-Analysis Results 27913.5 Communicating Insights in the Illustrative Examples 28013.5.1 Roughneck North America Strategy 28013.5.2 Geneptin 28013.5.3 Data Center Location 28113.6 Summary 281Key Terms 282References 28214 Enable Decision Implementation 28514.1 Introduction 28514.2 Barriers to Involving Decision Implementers 28614.3 Involving Decision Implementers in the Decision Process 28714.4 Using Decision Analysis for Decision and Strategy Implementation 28914.4.1 Using the Decision Model for Decision Implementation 28914.4.2 Using Decision-Analysis Models to Support Decision Implementation 28914.4.2.1 Example 1: Gas Plant Implementation 28914.4.2.2 Example 2: Information Assurance Program Progress 29014.4.3 Using Decision Analysis to Assess Strategy Implementation 29114.4.3.1 Example 29214.5 Illustrative Examples 29214.5.1 Data Center 29214.5.2 Rnas 29314.6 Summary 293Key Term 293References 29315 Summary of Major Themes 29515.1 Overview 29615.2 Decision Analysis Helps Answer Important Decision-Making Questions 29615.3 The Purpose of Decision Analysis Is to Identify and Create Value for Shareholders and Stakeholders 29715.3.1 Single Objective Value 29815.3.2 Multiple Objective Value 29815.3.3 It Is Important to Distinguish Potential Value and Implemented Value 29815.4 Decision Analysis Is a Sociotechnical Process 29815.4.1 Social 29815.4.2 Technical 29815.5 Decision Analysts Need Decision-Making Knowledge and Soft Skills 29815.5.1 Decision Analysts Need to Understand Decision-Making Challenges 29915.5.2 Decision Analysts Must Develop Their Soft Skills 29915.6 The Decision-Analysis Process Must Be Tailored to the Decision and the Organization 30015.6.1 Decision Quality 30015.6.2 Decision Processes 30015.6.2.1 Decision Conferencing 30015.6.3 Dialogue Decision Process 30015.7 Decision Analysis Enables Data-Driven Decision-Making 30115.8 Decision Analysis Offers Powerful Analytic Tools to Support Decision-Making 30115.8.1 Decision Framing 30215.8.2 Identifying Objectives and Value Measures 30215.8.3 Developing Creative Alternatives 30215.8.4 Building Decision Models 30215.8.5 Performing Deterministic Analysis 30215.8.6 Identifying Uncertainties 30315.8.7 Performing Probabilistic Analysis 30315.8.8 Performing Portfolio Resource Allocation 30315.9 Conclusion 304Appendix A Probability Theory 305A. 1 Introduction 305A. 2 Distinctions and the Clairvoyance Test 305A. 3 Possibility Tree Representation of a Distinction 306A. 4 Probability as an Expression of Degree of Belief 307A. 5 Inferential Notation 307A. 6 Multiple Distinctions 307A. 7 Joint, Conditional, and Marginal Probabilities 307A.8 Calculating Joint Probabilities 308A.9 Dependent and Independent Probabilities 309A.10 Reversing Conditional Probabilities – Bayes’ Rule 310A.11 Probability Distributions 311A.11.1 Summary Statistics for a Probability Distribution 312A.12 Combining Uncertain Quantities 312References 313Appendix B Decision Conferencing 315B. 1 Introduction 315B. 2 Decision Conference Process and Format 317B. 3 Location, Facilities, and Equipment 317B. 4 Use of Group Processes 318B. 5 Advantages and Disadvantages 319B. 6 Best Practices 321B. 7 Summary 322Key Terms 322References 323Appendix C Resource Allocation with Incremental Benefit/Cost Analysis 325C. 1 Multiple Objective Portfolio Analysis with Resource Constraints 325C.. 1 Characteristics of Incremental Benefit/Cost Portfolio Analysis 325C.1. 2 Algorithm for Incremental Benefit/Cost Portfolio Analysis 326C..2. 1 Identify the Objective 326C.1.. 2 Generate Options 326C.1.2. 3 Assess Costs 328C.1.2. 4 Assess Benefits 329C.1.2. 5 Specify Constraints 330C.1.2. 6 Allocate Resources 331C.1.2. 7 Perform Sensitivity Analysis 332C.1. 3 Application to the Data Center Portfolio 332C.1. 4 Comparison with Portfolio Optimization 337C.1. 5 Strengths and Weaknesses of Incremental Benefit/Cost Portfolio Analysis 338C. 2 Summary 338Key Terms 339References 340Appendix D Roughneck North American Strategy 341D.1 Context 341D.2 Decision Process 342D.3 Framing 342D.4 Objectives and Value Measures 342D.5 Alternatives 344D.6 Uncertainty Structuring 344D.7 Uncertainty Quantification 347D.8 Evaluation Logic (Spreadsheet Model) 347D.8.1 Selectors 347D.8. 2 Inputs Sheet 348D.8. 3 Strategy Table Sheet 348D.8. 4 Calculations Sheets 348D. 9 Probabilistic Analysis 349D. 10 Real Options 355D. 11 Portfolio Resource Allocation 358Reference 360Index 361