J
James O. Berger
Researcher at Duke University
Publications - Â 241
Citations - Â 39178
James O. Berger is an academic researcher from Duke University. The author has contributed to research in topics: Prior probability & Bayesian probability. The author has an hindex of 71, co-authored 241 publications receiving 36488 citations. Previous affiliations of James O. Berger include University of Valencia & University College London.
Papers
More filters
Journal ArticleDOI
Generalized Bayes Estimators in Multivariate Problems
James O. Berger,C. Srinivasan +1 more
TL;DR: In this article, a characterization of admissible estimators as generalized Bayes estimators is developed for certain multivariate exponential families and quadratic loss, and the problem of verifying whether or not an estimator is generalized bayes is also considered.
Journal ArticleDOI
Predicting Vehicle Crashworthiness: Validation of Computer Models for Functional and Hierarchical Data
Maria J. Bayarri,James O. Berger,Marc C. Kennedy,Athanasios Kottas,Rui Paulo,J Sacks,John A. Cafeo,Chin-Hsu Lin,Jian Tu +8 more
TL;DR: This study addresses the problem of validating the computer model for vehicle design goals by extending existing Gaussian process-based methodology developed for models that produce real-valued output, and resort to Bayesian hierarchical modeling to attack problem.
Journal ArticleDOI
Bayesian analysis of dynamic item response models in educational testing
TL;DR: In this article, a new class of state space models, called Dynamic Item Response (DIR) models, is proposed, which can be applied either retrospectively to the full data or on-line, in cases where real-time prediction is needed.
Journal ArticleDOI
Intervals for posttest probabilities: a comparison of 5 methods.
Douglas Mossman,James O. Berger +1 more
TL;DR: This work describes 5 methods of constructing confidence intervals for posttest probabilities when estimates of sensitivity, specificity, and the pretest probability of a disorder are derived from empirical data, and concludes that an objective Bayesian approach is the best approach.
Objective Bayesian Analysis for the Multivariate Normal Model
Dongchu Sun,James O. Berger +1 more
TL;DR: Objective Bayesian inference for the multivariate normal distribution is illustrated, using different types of formal objective priors (Jeffreys, invariant, reference and matching), different modes of inference (Bayesian and frequentist), and different criteria involved in selecting optimal objective priours.