Testing composite hypotheses, Hermite polynomials and optimal estimation of a nonsmooth functional

DOI10.1214/10-AOS849MaRDI QIDQ548545zbMATH OpenFDO

Authors Mark G. Low, T. Tony Cai

Publication date 29 June 2011

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

Full work available at URL https://arxiv.org/abs/1105.3039

zbMATH Keywords

\(\ell_1\) normbest polynomial approximationcomposite hypothesesHermite polynomialminimax lower boundnonsmooth functionaloptimal rate of convergence

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20)

Abstract: A general lower bound is developed for the minimax risk when estimating an arbitrary functional. The bound is based on testing two composite hypotheses and is shown to be effective in estimating the nonsmooth functional $frac1nsum|het{a}_i|$ from an observation $YsimN(heta,I_n)$. This problem exhibits some features that are significantly different from those that occur in estimating conventional smooth functionals. This is a setting where standard techniques fail to yield sharp results. A sharp minimax lower bound is established by applying the general lower bound technique based on testing two composite hypotheses. A key step is the construction of two special priors and bounding the chi-square distance between two normal mixtures. An estimator is constructed using approximation theory and Hermite polynomials and is shown to be asymptotically sharp minimax when the means are bounded by a given value $M$. It is shown that the minimax risk equals $$ asymptotically, where $$ is the Bernstein constant. The general techniques and results developed in the present paper can also be used to solve other related problems.

Recommendations

• Asymptotically Optimal Tests for Verifying Composite Finite-Parameter Hypotheses
• Testing composite hypotheses via convex duality
• Minimax testing of a composite null hypothesis defined via a quadratic functional in the model of regression
• Asymptotically minimax tests of some nonstandard composite hypotheses
• Nonparametric estimation of composite functions
• Hypothesis testing under composite functions alternative
• scientific article; zbMATH DE number 1054335
• A new approximate point optimal test of a composite null hypothesis

Cites work

• A constrained risk inequality with applications to nonparametric functional estimation
• Asymptotic methods in statistical decision theory
• Convergence of estimates under dimensionality restrictions
• Effect of mean on variance function estimation in nonparametric regression
• Geometrizing rates of convergence. II
• scientific article; zbMATH DE number 4107941 (Why is no real title available?)
• scientific article; zbMATH DE number 48688 (Why is no real title available?)
• Introduction to nonparametric estimation
• Minimax estimation of linear functionals over nonconvex parameter spaces.
• Nonquadratic estimators of a quadratic functional
• ON A CONJECTURE OF S. BERNSTEIN IN APPROXIMATION THEORY
• On estimation of the \(L_r\) norm of a regression function
• Some coefficient estimates for polynomials on the unit interval

Cited in

(33)

• Geometrizing rates of convergence. II
• Minimax Euclidean separation rates for testing convex hypotheses in \(\mathbb{R}^{d}\)
• Estimating linear functionals of a sparse family of Poisson means
• Chebyshev polynomials, moment matching, and optimal estimation of the unseen
• Adaptive estimation of the sparsity in the Gaussian vector model
• Efficient multivariate entropy estimation via \(k\)-nearest neighbour distances
• Sample complexity of the distinct elements problem
• On being Bayes and unbiasedness. Bayes and unbiasedness
• Adaptive estimation of high-dimensional signal-to-noise ratios
• Optimal rates of entropy estimation over Lipschitz balls
• Optimal sparsity testing in linear regression model
• Minimax estimation of norms of a probability density. I: Lower bounds
• On estimation of nonsmooth functionals of sparse normal means
• Optimal rates of estimation for multi-reference alignment
• Multidimensional linear functional estimation in sparse Gaussian models and robust estimation of the mean
• Estimating minimum effect with outlier selection
• Adaptive confidence intervals for regression functions under shape constraints
• Tight minimax rates for manifold estimation under Hausdorff loss
• Adaptive estimation of nonparametric functionals
• Estimation of Simultaneous Signals Using Absolute Inner Product with Applications to Integrative Genomics
• Optimal Estimation of Wasserstein Distance on a Tree With an Application to Microbiome Studies
• Estimation under group actions: recovering orbits from invariants
• Sparse signal detection in heteroscedastic Gaussian sequence models: sharp minimax rates
• Optimal estimation of Schatten norms of a rectangular matrix
• Dualizing Le Cam's method for functional estimation. I: General theory
• Tests of missing completely at random based on sample covariance matrices
• Sparsity meets correlation in Gaussian sequence model
• Universal bias reduction in estimation of smooth additive function in high dimensions
• Sharp convergence rates of empirical unbalanced optimal transport for spatio-temporal point processes
• Approximate independence of permutation mixtures
• The fundamental limits of structure-agnostic functional estimation
• Estimation and inference for the Wasserstein distance between mixing measures in topic models
• On estimation of L_r-norms in Gaussian white noise models

This page was built for publication: Testing composite hypotheses, Hermite polynomials and optimal estimation of a nonsmooth functional

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q548545)