Elicitation is a key task for subjectivist Bayesians. Although skeptics hold that elicitation cannot (or perhaps should not) be done, in practice it brings statisticians closer to their clients and subject-matter expert colleagues. This article reviews the state of the art, reflecting the experience of statisticians informed by the fruits of a long line of psychological research into how people represent uncertain information cognitively and how they respond to questions about that information. In a discussion of the elicitation process, the first issue to address is what it means for an elicitation to be successful; that is, what criteria should be used. Our answer is that a successful elicitation faithfully represents the opinion of the person being elicited. It is not necessarily “true” in some objectivistic sense, and cannot be judged in that way. We see that elicitation as simply part of the process of statistical modeling. Indeed, in a hierarchical model at which point the likelihood ends and the pr...

Statistical Methods for Eliciting Probability Distributions

This paper presents the present philosophy and practice used in probability encoding by the Decision Analysis Group at Stanford Research Institute. Probability encoding, the process of extracting and quantifying individual judgment about uncertain quantities, is one of the major functions required in the performance of decision analysis. The paper discusses the setting of the encoding process, including the use of sensitivity analyses to identify crucial state variables for which extensive encoding procedures are appropriate. The importance of balancing modeling and encoding techniques is emphasized and examples of biases and unconscious modes of judgment are reviewed. A variety of encoding methods are presented and their applicability is discussed. The authors recommend and describe a structured interview process that utilizes a trained interviewer and a number of techniques designed to reduce biases and aid in the quantification of judgment.

/pdf/exceptional-paper-probability-encoding-in-decision-analysis-3hoggt5f8d.pdf

Exceptional Paper---Probability Encoding in Decision Analysis

Calibration and probability judgements: Conceptual and methodological issues

Summary Statistical education now takes place in a new social context. It is influenced by a movement to reform the teaching of the mathematical sciences in general. At the same time, the changing nature of our discipline demands revised content for introductory instruction, and technology strongly influences both what we teach and how we teach. The case for substantial change in statistics instruction is built on strong synergies between content, pedagogy, and technology. Statisticians who teach beginners should become more familiar with research on teaching and learning and with changes in educational technology. The spirit of contemporary introductions to statistics should be very different from the traditional emphasis on lectures and on probability and inference.

/pdf/new-pedagogy-and-new-content-the-case-of-statistics-kkdf00ty6l.pdf

New Pedagogy and New Content: The Case of Statistics

1. Introduction 2. Critiques of statistical methods 3. Analysing averages and frequencies 4. How good are the models? 5. Regression and correlation 6. Analysis of variance Case studies 7. Mark-recapture analysis 8. Effects of marking frogs 9. Population dynamics 10. Subjective priors 11. Conclusion Appendix A. A tutorial for running WinBUGS Appendix B. Probability distributions Appendix C. MCMC algorithms.

/pdf/bayesian-methods-for-ecology-3tg8hj8e6u.pdf

Bayesian Methods for Ecology

SUMMARY Subjective probability is defined and its place in decision analysis, with special reference to business problems, is identified. The literature on its measurement is critically analysed both for the single decision-maker and group. The use of direct fractile assessment and the Delphi Technique are felt to be some of the more tenable of the methods reviewed. An account of some of the behavioural aspects of decision-making with a resume of the "risky" shift theories is included and their implications are discussed. Some practical guidelines and suggestions for further research are indicated.

Subjective Probability and its Measurement

SUMMARY The different methods which have been suggested for measuring unidimensional and multidimensional utility functions in business and related fields are described and discussed. The factors which should influence the measurement method chosen in a given decision-making situation are explicitly considered. The concept of group utility and the procedures which exist for formulating a coherent risk policy for a whole organization are described. Several practical applications of utility theory are given and conclusions reached as to those areas where further research is needed.

https://www.jstor.org/stable/pdfplus/2345110.pdf

Utility and its Measurement

The Working Party was set up by the Royal Statistical Society because of widespread criticism of UK official statistics collected and reported by the Government Statistical Service. That Service has to be of fine quality, earning and enjoying public confidence and providing accurate, timely and cost-effective data both for governmental and for public use. The Working Party found no evidence of a lack of integrity among government statisticians. However, the organizational and operational framework of the Government Statistical Service is regarded as inadequate. Accordingly four important sets of recommendations are made. Their acceptance is fundamental for the achievement of a high quality of service linked to full public confidence in official statistics.

Official Statistics: Counting with Confidence

This paper reviews the development of higher education since the end of the Second World War and explores the way it has been marketed over that period. The advent of a marketing concept is dated from the early 1960s, with the establishment of UCCA and the great public relations effect of the Robbins Report. The final sections of the paper explore the concept of strategic planning in higher education and the development of marketing strategies within a strategic plan.

Marketing Higher Education

This paper outlines the build-up of the National Lottery launch, from the government 1992 white paper, the subsequent Parliamentary procedures leading to the National Lottery Act, the choice of Camelot as the operator in May 1994 and the nationwide launch of the lottery in November 1994. The paper outlines the achievements of the lottery and some longer-term issues that it faces.

Peter G. Moore

Papers

Subjective Probability and its Measurement

Utility and its Measurement

Official Statistics: Counting with Confidence

Marketing Higher Education

The Development of the UK National Lottery: 1992–96