Abstract

of least relative surprise; model checking; change of variable problem; crossvalidation. We consider the problem of deriving Bayesian inference procedures via the concept of relative surprise. The mathematical concept of surprise has been developed by I.J. Good in a long sequence of papers. We make a modiÞcation to this development that permits the avoidance of a serious defect; namely, the change of variable problem. We apply relative surprise to the development of estimation, hypothesis testing and model checking procedures. Important advantages of the relative surprise approach to inference include the lack of dependence on a particular loss function and complete freedom to the statistician in the choice of prior for hypothesis testing problems. Links are established with common Bayesian inference procedures such as highest posterior density regions, modal estimates and Bayes factors. From a practical perspective new inference

Citations

717	Bayes factors - Kass, Raftery - 1995
126	Bayesian model choice: Asymptotics and exact calculations - Gelfand, Dey - 1994
70	Sellke T: Testing a point null hypothesis: The irreconcilability of P-values and evidence - Berger - 1987
67	Good Thinking: The Foundations of Probability and Its Applications - Good - 1983
47	Present position and potential developments: Some personal views, statistical theory, the prequential approach - Dawid - 1984
46	D: A statistical paradox - Lindley - 1957
28	Mathematical Statistics and Data Analysis. Second edition - Rice - 1995
25	Reconciling Bayesian and frequentist evidence in the one-sided testing problem - Casella, RL - 1987
25	Marginalization paradoxes in Bayesian and structural inference (with discussion - Dawid, Stone, et al. - 1973
24	Posterior Bayes factor (with discussion - Aitkin - 1991
16	Testing precise hypotheses (with discussion - DELAMPADY - 1987
9	The surprise index for the multivariate normal distribution - Good - 1956
8	A Note on Jeffreys-Lindley Paradox - Robert - 1993
6	Some logic and history of hypothesis testing - GOOD - 1983
6	Some remarks on estimating a noncentrality parameter - Perlman, Rasmussen - 1975
4	Surprise index, in Encyclopaedia of Statistical Sciences,Vol.7 - Good
4	Estimation of the non-centrality parameter of a chi squared distribution - Saxena, Alam
3	The probabilistic explication of information, evidence, surprise, causality, explanation, and utility - Good - 1971
2	Sampling and Bayes’ inference in scientiÞc modelling and robustness - Box - 1980
2	The appropriate mathematical tools for describing and measuring uncertainty - Good - 1953
2	Perspectives in Probability and - Gani, J - 1992
2	Comment (on Patil and Taillie: Diversity as a Concept and its Measurement - Good - 1982
2	indices and p-values - Good, Surprise
2	Stimulus probability, surprise and reaction time - Kvalseth - 1987
1	The statistical signiÞcance of odd bits of information - Bartlett
1	Predictive Inference: An Introduction. NewYork:Chapman and - Geisser - 1993
1	Posterior predictive assessment of model Þtness via realized discrepancies - Gelman, Meng, et al. - 1995
1	A new Þnite series for Legendre polynomials - Good
1	Comment on Shafer, Constructive Probability - Good
1	Antisurprise - Good
1	A new measure of surprise - Good
1	Potential surprise in the context of inquiry. Uncertainty and Expectations in Economics - Levi
1	A note on the surprise index - M
1	An example of wide discrepancy between Þducial and conÞdence intervals - Stein - 1959
1	Probability, rarity, interest and surprise", ScientiÞcMonthly - Weaver - 1948