Decision theory and large deviations for dynamical hypotheses tests: the Neyman-Pearson lemma, min-max and Bayesian tests

DOI10.3934/JDG.2021031zbMATH Open1486.62017arXiv2101.08227OpenAlexW4205883758MaRDI QIDQ2140235FDOQ2140235

Authors: Hermes H. Ferreira, A. O. Lopes, Sílvia R. C. Lopes 

Publication date: 20 May 2022

Published in: Journal of Dynamics and Games (Search for Journal in Brave)

Abstract: We analyze hypotheses tests using classical results on large deviations to compare two models, each one described by a different H"older Gibbs probability measure. One main difference to the classical hypothesis tests in Decision Theory is that here the two measures are singular with respect to each other. Among other objectives, we are interested in the decay rate of the wrong decisions probability, when the sample size $n$ goes to infinity. We show a dynamical version of the Neyman-Pearson Lemma displaying the ideal test within a certain class of similar tests. This test becomes exponentially better, compared to other alternative tests, when the sample size goes to infinity. We are able to present the explicit exponential decay rate. We also consider both, the Min-Max and a certain type of Bayesian hypotheses tests. We shall consider these tests in the log likelihood framework by using several tools of Thermodynamic Formalism. Versions of the Stein's Lemma and Chernoff's information are also presented.

Full work available at URL: https://arxiv.org/abs/2101.08227

Recommendations

• Dynamical hypothesis tests and decision theory for Gibbs distributions
• Averaging of the Neumann problems for nonlinear elliptic equations in domains with accumulators
• Large-deviation theorems in hypothesis-testing problems
• Publication:4939962
• On many hypotheses logarithmically asymptotically optimal testing via the theory of large deviations

zbMATH Keywords

decision theorythermodynamic formalismNeyman-Pearson Lemmarejection regionlarge deviations propertiesBayesian hypotheses testGibbs probabilitiesmin-max hypotheses test

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Minimax procedures in statistical decision theory (62C20) Thermodynamic formalism, variational principles, equilibrium states for dynamical systems (37D35)

Cites Work

• Entropy and large deviation
• Title not available (Why is that?)
• Large deviations techniques and applications.
• Escort distributions minimizing the Kullback-Leibler divergence for a large deviations principle and tests of entropy level
• Large Deviations in Dynamical Systems and Stochastic Processes
• Large deviations for empirical entropies ofg-measures
• Entropy, large deviations, and statistical mechanics.
• Title not available (Why is that?)
• Ergodic optimization, zero temperature limits and the max-plus algebra. Paper from the 29th Brazilian mathematics colloquium -- 29\(^{\text o}\) Colóquio Brasileiro de Matemática, Rio de Janeiro, Brazil, July 22 -- August 2, 2013
• On entropy production of repeated quantum measurements. I. General theory
• Circular unitary ensembles: parametric models and their asymptotic maximum likelihood estimates
• Title not available (Why is that?)
• Nonequilibrium in thermodynamic formalism: the second law, gases and information geometry
• On information gain, Kullback-Leibler divergence, entropy production and the involution kernel
• Gibbs posterior convergence and the thermodynamic formalism
• Title not available (Why is that?)
• Title not available (Why is that?)
• An iterative process for approximating subactions
• Bayes posterior convergence for loss functions via almost additive thermodynamic formalism
• Different closed-form expressions for generalized entropy rates of Markov chains
• Binary Hypothesis Testing Game With Training Data
• A Bayesian approach for estimating the parameters of an α-stable distribution
• Power of the likelihood ratio test for models of DNA base substitution

Cited In (2)

• Dynamical hypothesis tests and decision theory for Gibbs distributions
• Explicit bivariate rate functions for large deviations in AR(1) and MA(1) processes with Gaussian innovations

This page was built for publication: Decision theory and large deviations for dynamical hypotheses tests: the Neyman-Pearson lemma, min-max and Bayesian tests

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2140235)