Jeffreys' prior is asymptotically least favorable under entropy risk

DOI10.1016/0378-3758(94)90153-8zbMath0820.62006OpenAlexW2057393527WikidataQ56168370 ScholiaQ56168370MaRDI QIDQ1333128

Andrew R. Barron, Bertrand S. Clarke

Publication date: 14 September 1995

Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0378-3758(94)90153-8

zbMATH Keywords

relative entropydata compressionFisher informationJeffreys' priorBayes riskminimax riskreference priorchannel capacitysource codingShannon's mutual informationmaximum entropy priorasymptotic expressionprobabilistic codingcontinuous positive priorsKullback- Leibler distancelarge sample decision theoretic propertiesleast favorable priorsmaximin risk

Mathematics Subject Classification ID

Bayesian inference (62F15) Bayesian problems; characterization of Bayes procedures (62C10) Minimax procedures in statistical decision theory (62C20) Statistical aspects of information-theoretic topics (62B10)

Related Items

Overall objective priors, Partial information reference priors: Derivation and interpretations, Information optimality and Bayesian modelling, Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory, Simultaneous prediction of independent Poisson observables, A new approach to default priors and robust bayes methodology, Reference priors via \(\alpha \)-divergence for a certain non-regular model in the presence of a nuisance parameter, Asymptotically minimax Bayes predictive densities, Regularized Aggregation of One-Off Probability Predictions, Information tradeoff, Reference priors in multiparameter nonregular cases, Moment matching priors, Schwarz, Wallace, and Rissanen: Intertwining Themes in Theories of Model Selection, Competitive On-line Statistics, Probabilistic Models for Bacterial Taxonomy, On model selection, Bayesian networks, and the Fisher information integral, Bayesian prediction based on a class of shrinkage priors for location-scale models, Local sensitivity of posterior expectations, Mutual information, metric entropy and cumulative relative entropy risk, Enhancing quantum annealing performance for the molecular similarity problem, Analytical derivation of the reference prior by sequential maximization of Shannon's mutual information in the multi-group parameter case, A decision-theoretical view of default priors, Ranking Forecasts by Stochastic Error Distance, Information and Reliability Measures, Optimal, reliable estimation of quantum states, Predicting a binary sequence almost as well as the optimal biased coin, Applications of Laplace’s method in Bayesian analysis and related topics, Inference in two-piece location-scale models with Jeffreys priors, On divergence measures leading to Jeffreys and other reference priors, A general divergence criterion for prior selection, Asymptotically minimax Bayesian predictive densities for multinomial models, A Bernstein-von Mises theorem for discrete probability distributions, Reference priors for exponential families with increasing dimension, Unnamed Item, Objective priors: an introduction for frequentists, Discussion on ``Objective priors: an introduction for frequentists by M. Ghosh, Eliciting vague but proper maximal entropy priors in Bayesian experiments, Shannon optimal priors on independent identically distributed statistical experiments converge weakly to Jeffrey's prior, Learning genetic population structures using minimization of stochastic complexity, Comparative noninformativities of quantum priors based on monotone metrics, Catching up Faster by Switching Sooner: A Predictive Approach to Adaptive Estimation with an Application to the AIC–BIC Dilemma, Unnamed Item, Asymptotic Theory of Information-Theoretic Experimental Design, Jeffreys versus Shtarkov distributions associated with some natural exponential families, Nonsubjective priors via predictive relative entropy regret, Universal approximation of multi-copy states and universal quantum lossless data compression, Conjugate Priors Represent Strong Pre-Experimental Assumptions, Bayesian predictive densities based on latent information priors, A minimally informative likelihood for decision analysis: Illustration and robustness, An empirical study of minimum description length model selection with infinite parametric complexity, Optimal compromise between incompatible conditional probability distributions, with application to Objective Bayesian Kriging, Propriety of the reference posterior distribution in Gaussian process modeling, The formal definition of reference priors, A scaling law from discrete to continuous solutions of channel capacity problems in the low-noise limit, Information-theoretic determination of minimax rates of convergence, Learning Bayesian network parameters via minimax algorithm, Failure-time prediction, Reference priors for prediction, The maximum likelihood prior, Quantum and Fisher information from the Husimi and related distributions, Bayesian predictiveness, exchangeability and sufficientness in bacterial taxonomy

Cites Work

• Bayes theory
• A decomposition for the likelihood ratio statistic and the Bartlett correction - a Bayesian argument
• Stochastic complexity and modeling
• On obtaining invariant prior distributions
• Reference priors for the orbit in a group model
• Some Remarks on Noninformative Priors
• Information-theoretic asymptotics of Bayes methods
• Noninformative priors for one parameter of many
• A source matching approach to finding minimax codes
• The performance of universal encoding
• Ordered group reference priors with application to the multinomial problem
• Goodness of prediction fit
• Estimating a Product of Means: Bayesian Analysis with Reference Priors
• Universal noiseless coding
• The Asymptotically Unbiased Prior Distribution
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item