Minimax optimal sequential hypothesis tests for Markov processes

DOI10.1214/19-AOS1899zbMATH Open1460.62131arXiv1811.04286OpenAlexW3087611683MaRDI QIDQ2215752FDOQ2215752

Authors: Michael Fauß, Abdelhak M. Zoubir, H. Vincent Poor 

Publication date: 14 December 2020

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: Under mild Markov assumptions, sufficient conditions for strict minimax optimality of sequential tests for multiple hypotheses under distributional uncertainty are derived. First, the design of optimal sequential tests for simple hypotheses is revisited and it is shown that the partial derivatives of the corresponding cost function are closely related to the performance metrics of the underlying sequential test. Second, an implicit characterization of the least favorable distributions for a given testing policy is stated. By combining the results on optimal sequential tests and least favorable distributions, sufficient conditions for a sequential test to be minimax optimal under general distributional uncertainties are obtained. The cost function of the minimax optimal test is further identified as a generalized $f$-dissimilarity and the least favorable distributions as those that are most similar with respect to this dissimilarity. Numerical examples for minimax optimal sequential tests under different uncertainties illustrate the theoretical results.

Full work available at URL: https://arxiv.org/abs/1811.04286

Recommendations

• A linear programming approach to sequential hypothesis testing
• Optimal Sequential Tests for Two Simple Hypotheses
• Optimal sequential multiple hypothesis tests
• Optimal sequential tests for two simple hypothesis based on independent observations
• Optimal sequential tests for testing two composite and multiple simple hypotheses
• Optimal multistage sequential hypothesis testing
• Sequential Procedure of Testing Composite Hypotheses with Applications to the Kiefer–Weiss Problem
• Sequential joint detection and estimation
• Minimax Sequential Tests for Many Composite Hypotheses. I

zbMATH Keywords

multiple hypothesis testingsequential analysisrobust hypothesis testingminimax proceduresdistributional uncertainty

Mathematics Subject Classification ID

Sequential statistical analysis (62L10) Markov processes: hypothesis testing (62M02) Minimax procedures in statistical decision theory (62C20) Robustness and adaptive procedures (parametric inference) (62F35)

Cites Work

• Robust Statistics for Signal Processing
• Title not available (Why is that?)
• Robust Statistics
• Sequential analysis. Tests and confidence intervals
• Minimax Methods for Multihypothesis Sequential Testing and Change-Point Detection Problems
• Title not available (Why is that?)
• Robust Statistics
• Robust techniques for signal processing: A survey
• Title not available (Why is that?)
• A Robust Version of the Probability Ratio Test
• Title not available (Why is that?)
• Integrals which are convex functionals
• Robust and efficient estimation by minimising a density power divergence
• Parameter estimation for binomial \(\mathrm{AR}(1)\) models with applications in finance and industry
• Theory of capacities
• Title not available (Why is that?)
• Minimax tests and the Neyman-Pearson lemma for capacities
• On minimax robustness: A general approach and applications
• An introduction to continuous-time stochastic processes. Theory, models, and applications to finance, biology, and medicine
• Quickest Detection
• On surrogate loss functions and \(f\)-divergences
• Optimal sequential multiple hypothesis tests
• Sequential detection of targets in multichannel systems
• 2-SPRT's and the modified Kiefer-Weiss problem of minimizing an expected sample size
• Sequential Procedure of Testing Composite Hypotheses with Applications to the Kiefer–Weiss Problem
• Some Properties of Generalized Sequential Probability Ratio Tests
• Information, Divergence and Risk for Binary Experiments
• Robust decision design using a distance criterion
• On the construction of least favourable pairs of distributions
• Construction of minimax tests for bounded families of probability densities
• Measuring distribution model risk
• f-dissimilarity: A generalization of the affinity of several distributions
• Title not available (Why is that?)
• Robust sequential detection of signals in noise
• Robust hypothesis testing for bounded classes of probability densities (Corresp.)
• Minimax Robust Quickest Change Detection
• Sequential Decision Problems for Processes with Continuous time Parameter. Testing Hypotheses
• Sequential change-point detection for mixing random sequences under composite hypotheses
• Minimax Sequential Tests of Some Composite Hypotheses
• Title not available (Why is that?)
• Convex integral functionals
• Almost optimal sequential tests of discrete composite hypotheses
• A robust approach to sequential detection
• Title not available (Why is that?)
• Binomial \(\mathrm{AR}(1)\) processes: moments, cumulants, and estimation
• Bayes Risk Error is a Bregman Divergence
• Nearly minimax one-sided mixture-based sequential tests
• Data-Efficient Minimax Quickest Change Detection With Composite Post-Change Distribution
• Asymptotic Solution of the Kiefer–Weiss Problem for Processes with Independent Increments
• Robust Hypothesis Testing with <inline-formula> <tex-math notation="LaTeX">$\alpha $</tex-math> </inline-formula>-Divergence
• Old Bands, New Tracks—Revisiting the Band Model for Robust Hypothesis Testing
• A Linear Programming Approach to Sequential Hypothesis Testing
• The optimal decision rule in the Kiefer-Weiss problem for a Brownian motion

Cited In (2)

• Title not available (Why is that?)
• An optimal sequential procedure for determining the drift of a Brownian motion among three values

Uses Software

• robustbase

This page was built for publication: Minimax optimal sequential hypothesis tests for Markov processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215752)