Experts in Uncertainty: Opinion and Subjective Probability in ScienceThis book is an extensive survey and critical examination of the literature on the use of expert opinion in scientific inquiry and policy making. The elicitation, representation, and use of expert opinion is increasingly important for two reasons: advancing technology leads to more and more complex decision problems, and technologists are turning in greater numbers to "expert systems" and other similar artifacts of artificial intelligence. Cooke here considers how expert opinion is being used today, how an expert's uncertainty is or should be represented, how people do or should reason with uncertainty, how the quality and usefulness of expert opinion can be assessed, and how the views of several experts might be combined. He argues for the importance of developing practical models with a transparent mathematic foundation for the use of expert opinion in science, and presents three tested models, termed "classical," "Bayesian," and "psychological scaling." Detailed case studies illustrate how they can be applied to a diversity of real problems in engineering and planning. |
Contents
SUBJECTIVE PROBABILITY | 85 |
COMBINING EXPERT OPINIONS | 169 |
Appendix A Mathematical Framework and Interpretation | 273 |
Appendix B Standard normal inverse normal Chi square coefficient of agreement coefficient of concordance | 285 |
References | 299 |
315 | |
319 | |
Other editions - View all
Experts in Uncertainty: Opinion and Subjective Probability in Science Roger Cooke Limited preview - 1991 |
Common terms and phrases
applications assume assumptions asymptotic B₁ B₂ base rate base rate fallacy Bayesian model C₁ calibration score certainty factors Chapter classical model conditional probability consider correlation decision maker defined Delphi Delphi method denote density discussed elicitation ESTEC-2 estimate evaluating example expert assessments expert opinion expert systems failure finite forecasting fuzzy fuzzy sets given Hence Human Reliability hypothesis independent indicator function intrinsic range Item Kahn large number Lemma loss function mathematical mean measure MYCIN normal Nuclear observations optimization outcomes P₁ paired comparison parameters performance possible preference probabilistic probability assessments probability vector problem proof proper scoring rules Proposition quantile tests quantiles random variable rank rational Reactor Safety Study relative frequencies Reliability risk analysis sample distribution Savage's seed variables sequence strictly proper subjective probability Suppose Table theorem theory true value Tversky uncertain quantities unnormalized vector weights
Popular passages
Page 7 - Despite a widespread belief to the contrary, objective studies indicate that even though the amount of human tragedy would be greatly increased in the postwar world, the increase would not preclude normal and happy lives for the majority of survivors and their descendants.