Optimal inference with a multidimensional multiscale statistic

DOI10.1214/21-EJS1914MaRDI QIDQ2074288zbMATH OpenFDO

Authors Pratyay Datta, Bodhisattva Sen

Publication date 9 February 2022

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1806.02194, https://projecteuclid.org/journals/electronic-journal-of-statistics/volume-15/issue-2/Optimal-inference-with-a-multidimensional-multiscale-statistic/10.1214/21-EJS1914.full

zbMATH Keywords

asymptotic minimax testingBrownian sheetHölder classes of functionskernel estimationmultivariate continuous white noise modelsignal detection on hyperrectangles

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20) Nonparametric regression and quantile regression (62G08) Nonparametric inference and fuzziness (62G86)

Abstract: We observe a stochastic process $Y$ on $[0,1{]}^d$ ($dgeq1$) satisfying $dY(t)=n^{1/2}f(t)dt$ + $dW(t)$, $tin[0,1{]}^d$, where $ngeq1$ is a given scale parameter (`sample size'), $W$ is the standard Brownian sheet on $[0,1{]}^d$ and $fin{L}_1([0,1{]}^d)$ is the unknown function of interest. We propose a multivariate multiscale statistic in this setting and prove its almost sure finiteness; this extends the work of D"umbgen and Spokoiny (2001) who proposed the analogous statistic for $d=1$. We use the proposed multiscale statistic to construct optimal tests for testing $f=0$ versus (i) appropriate H"{o}lder classes of functions, and (ii) alternatives of the form $f=m{u}_{n}mathbb{I}_{B_n}$, where $B_n$ is an axis-aligned hyperrectangle in $[0,1{]}^d$ and $m{u}_{n}inmathbbR$; $m{u}_n$ and $B_n$ unknown. In the process we generalize Theorem 6.1 of D"umbgen and Spokoiny (2001) about stochastic processes with sub-Gaussian increments on a pseudometric space, which is of independent interest.

Recommendations

• Multiscale testing of qualitative hypotheses
• Multiscale inference about a density
• Minimax optimal procedures for testing the structure of multidimensional functions
• scientific article; zbMATH DE number 5060485
• Multidimensional multiscale scanning in exponential families: limit theory and statistical consequences

Cites work

• A continuous Gaussian approximation to a nonparametric regression in two dimensions
• A martingale approach to scan statistics
• A spatial scan statistic
• Adaptive goodness-of-fit tests based on signed ranks
• An Adaptive, Rate-Optimal Test of a Parametric Mean-Regression Model Against a Nonparametric Alternative
• An extension of stochastic integrals in the plane
• Asymptotic equivalence for nonparametric regression with multivariate and random design
• Asymptotic equivalence of nonparametric regression and white noise
• Asymptotically exact nonparametric hypothesis testing in sup-norm and at a fixed point
• Asymptotically minimax hypothesis testing for nonparametric alternatives. I
• Asymptotically minimax hypothesis testing for nonparametric alternatives. II
• Asymptotically minimax hypothesis testing for nonparametric alternatives. III
• Detection of a sparse submatrix of a high-dimensional noisy matrix
• Detection of an anomalous cluster in a network
• Detection of spatial clustering with average likelihood ratio test statistics
• Detection with the scan and the average likelihood ratio
• Estimation and detection of functions from anisotropic Sobolev classes
• Estimation for the distribution of two-dimensional discrete scan statistics
• Exact asymptotics for the scan statistic and fast alternatives
• Exact convergence rate for the maximum of standardized Gaussian increments
• Functions of bounded variation, signed measures, and a general Koksma–Hlawka inequality
• Heterogeneous change point inference
• Maxima of partial sums indexed by geometrical structures
• Minimax goodness-of-fit testing in multivariate nonparametric regression
• Multidimensional multiscale scanning in exponential families: limit theory and statistical consequences
• Multiparameter Processes
• Multiple window and cluster size scan procedures
• Multiple Window Discrete Scan Statistics
• Multiscale change point inference. With discussion and authors' reply
• Multiscale inference about a density
• Multiscale inference for a multivariate density with applications to X-ray astronomy
• Multiscale inference for multivariate deconvolution
• Multiscale methods for shape constraints in deconvolution: confidence statements for qualitative features
• Multiscale scanning in inverse problems
• Multiscale testing of qualitative hypotheses
• Near-Optimal Detection of Geometric Objects by Fast Multiscale Methods
• Nonparametric goodness-of-fit testing under Gaussian models
• Optimal and fast detection of spatial clusters with scan statistics
• Optimal detection of a jump in the intensity of a Poisson process or in a density with likelihood ratio statistics
• Optimal detection of multi-sample aligned sparse signals
• Properties of higher criticism under strong dependence
• Rates of strong uniform consistency for multivariate kernel density estimators. (Vitesse de convergence uniforme presque sûre pour des estimateurs à noyaux de densités multivariées)
• Renormalization exponents and optimal pointwise rates of convergence
• Sharp minimax adaptation over Sobolev ellipsoids in nonparametric testing
• Tail probabilities for the null distribution of scanning statistics
• Using the generalized likelihood ratio statistic for sequential detection of a change-point
• Variable window scan statistics for normal data
• Weak convergence and empirical processes. With applications to statistics

Cited in

(8)

• Minimax optimal procedures for testing the structure of multidimensional functions
• Multiscale testing of qualitative hypotheses
• scientific article; zbMATH DE number 5629261 (Why is no real title available?)
• scientific article; zbMATH DE number 4070101 (Why is no real title available?)
• scientific article; zbMATH DE number 5060485 (Why is no real title available?)
• Optimal Multiple Decision Statistical Procedure for Inverse Covariance Matrix
• Sharp adaptive and pathwise stable similarity testing for scalar ergodic diffusions
• Multiscale scanning with nuisance parameters

Describes a project that uses

Uses Software

• HSMUCE

This page was built for publication: Optimal inference with a multidimensional multiscale statistic

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2074288)