James T. Peterson is the Assistant Unit Leader and Associate Professor for the USGS Oregon Cooperative Fish and Wildlife Research Unit at Oregon State University. He has been developing and teaching courses in applied quantitative decision making to undergraduate and graduate students and professionals in natural resource and related disciplines for more than a decade.

List of boxes xi

Preface xiii

Acknowledgements xiv

Guide to using this book xv

Companion website xvii

PART I. INTRODUCTION TO DECISION MAKING 1

1 Introduction: Why a Structured Approach in Natural Resources? 3

The role of decision making in natural resource management 4

Common mistakes in framing decisions 5

What is structured decision making (SDM)? 6

Why should we use a structured approach to decision making? 7

Limitations of the structured approach to decision making 8

Adaptive resource management 9

Summary 10

References 10

2 Elements of Structured Decision Making 13

First steps: defining the decision problem 13

General procedures for structured decision making 15

Predictive modeling: linking decisions to objectives prospectively 17

Uncertainty and how it affects decision making 18

Dealing with uncertainty in decision making 21

Summary 23

References 23

3 Identifying and Quantifying Objectives in Natural Resource Management 24

Identifying objectives 24

Identifying fundamental and means objectives 25

Clarifying objectives 28

Separating objectives from science 29

Barriers to creative decision making 30

Types of fundamental objectives 32

Identifying decision alternatives 34

Quantifying objectives 38

Dealing with multiple objectives 38

Multi-attribute valuation 41

Utility functions 43

Other approaches 50

Additional considerations 52

Decision, objectives, and predictive modeling 55

References 55

4 Working with Stakeholders in Natural Resource Management 57

Stakeholders and natural resource decision making 57

Stakeholder analysis 59

Stakeholder governance 62

Working with stakeholders 68

Characteristics of good facilitators 68

Getting at stakeholder values 71

Stakeholder meetings 72

The first workshop 74

References 76

Additional reading 76

PART II. TOOLS FOR DECISION MAKING AND ANALYSIS 77

5 Statistics and Decision Making 79

Basic statistical ideas and terminology 80

Using data in statistical models for description and prediction 100

Linear models 104

Hierarchical models 116

Bayesian inference 129

Resampling and simulation methods 140

Statistical significance 145

References 146

Additional reading 146

6 Modeling the Influence of Decisions 147

Structuring decisions 147

Influence diagrams 148

Frequent mistakes when structuring decisions 153

Defining node states 157

Decision trees 159

Solving a decision model 160

Conditional independence and modularity 164

Parameterizing decision models 165

Elicitation of expert judgment 179

Quantifying uncertainty in expert judgment 188

Group elicitation 189

The care and handling of experts 190

References 191

Additional reading 191

7 Identifying and Reducing Uncertainty in

Decision Making 192

Types of uncertainty 192

Irreducible uncertainty 193

Reducible uncertainty 194

Effects of uncertainty on decision making 197

Sensitivity analysis 203

Value of information 217

Reducing uncertainty 220

References 230

Additional reading 231

8 Methods for Obtaining Optimal Decisions 232

Overview of optimization 233

Factors affecting optimization 234

Multiple attribute objectives and constrained optimization 239

Dynamic decisions 246

Optimization under uncertainty 249

Analysis of the decision problem 253

Suboptimal decisions and "satisficing" 256

Other problems 257

Summary 258

References 258

PART III. APPLICATIONS 261

9 Case Studies 263

Case study 1 Adaptive Harvest Management of American Black Ducks 263

Case study 2 Management of Water Resources in the Southeastern US 276

Case study 3 Regulation of Largemouth Bass Sport Fishery in Georgia 284

Summary 291

References 291

10 Summary, Lessons Learned, and Recommendations 294

Summary 294

Lessons learned 294

Structured decision making for Hector's Dolphin conservation 295

Landowner incentives for conservation of early successional habitats in Georgia 298

Cahaba shiner 299

Other lessons 303

References 304

PART IV. APPENDICES 307

Appendix A Probability and Distributional Relationships 309

Probability axioms 309

Conditional probability 309

Conditional independence 310

Expected value of random variables 311

Law of total probability 311

Bayes' theorem 312

Distribution moments 313

Sample moments 316

Additional reading 316

Appendix B Common Statistical Distributions 317

General distribution characteristics 317

Continuous distributions 320

Discrete distributions 329

Reference 338

Additional Reading 338

Appendix C Methods for Statistical Estimation 339

General principles of estimation 339

Method of moments 342

Least squares 343

Maximum likelihood 346

Bayesian approaches 353

References 372

Appendix D Parsimony, Prediction, and Multi-Model Inference 373

General approaches to multi-model inference 373

Multi-model inference and model averaging 376

Multi-model Bayesian inference 380

References 383

Appendix E Mathematical Approaches to Optimization 384

Review of general optimization principles 385

Classical programming 392

Nonlinear programming 397

Linear programming 399

Dynamic decision problems 402

Decision making under structural uncertainty 419

Generalizations of Markov decision processes 427

Heuristic methods 427

References 429

Appendix F Guide to Software 430

Appendix G Electronic Companion to Book 432

Glossary 433

Index 449