Optimal calibration for multiple testing against local inhomogeneity in higher dimension
From MaRDI portal
(Redirected from Publication:639876)
Abstract: Based on two independent samples X_1,...,X_m and X_{m+1},...,X_n drawn from multivariate distributions with unknown Lebesgue densities p and q respectively, we propose an exact multiple test in order to identify simultaneously regions of significant deviations between p and q. The construction is built from randomized nearest-neighbor statistics. It does not require any preliminary information about the multivariate densities such as compact support, strict positivity or smoothness and shape properties. The properly adjusted multiple testing procedure is shown to be sharp-optimal for typical arrangements of the observation values which appear with probability close to one. The proof relies on a new coupling Bernstein type exponential inequality, reflecting the non-subgaussian tail behavior of a combinatorial process. For power investigation of the proposed method a reparametrized minimax set-up is introduced, reducing the composite hypothesis "p=q" to a simple one with the multivariate mixed density (m/n)p+(1-m/n)q as infinite dimensional nuisance parameter. Within this framework, the test is shown to be spatially and sharply asymptotically adaptive with respect to uniform loss on isotropic H"older classes. The exact minimax risk asymptotics are obtained in terms of solutions of the optimal recovery.
Recommendations
- Multivariate Two-Sample Tests Based on Nearest Neighbors
- A multivariate two-sample test based on the number of nearest neighbor type coincidences
- Hypothesis testing for densities and high-dimensional multinomials: sharp local minimax rates
- Optimal tests for the general two-sample problem
- Adaptive goodness-of-fit tests in a density model
Cites work
- scientific article; zbMATH DE number 5604036 (Why is no real title available?)
- scientific article; zbMATH DE number 4123079 (Why is no real title available?)
- scientific article; zbMATH DE number 3258670 (Why is no real title available?)
- A bound on the moment generating function of a sum of dependent variables with an application to simple random sampling without replacement
- A general class of exponential inequalities for martingales and ratios
- Adaptive goodness-of-fit tests based on signed ranks
- Adaptive hypothesis testing using wavelets
- Application of local rank tests to nonparametric regression
- Asymptotic equivalence of density estimation and Gaussian white noise
- Asymptotic minimax risk for sup-norm loss: Solution via optimal recovery
- Asymptotically exact nonparametric hypothesis testing in sup-norm and at a fixed point
- Asymptotics in statistics. Some basic concepts.
- Consistency and Monte Carlo simulation of a data driven version of smooth goodness-of-fit tests
- Convergence of stochastic processes
- Data Driven Rank Test for Two‐Sample Problem
- Data-Driven Version of Neyman's Smooth Test of Fit
- Efficient and adaptive nonparametric test for the two-sample problem
- Galton's test as a linear rank test with estimated scores and its local asymptotic efficiency
- H//0-contiguity in nonparametric testing problems and sample Pitman efficiency
- Local asymptotics for linear rank statistics with estimated score functions
- Multiscale inference about a density
- Multiscale testing of qualitative hypotheses
- Nonparametric homogeneity tests
- Nonparametric testing for a monotone hazard function via normalized spacings
- On the solution of an optimal recovery problem and its applications in nonparametric regression
- Optimal and fast detection of spatial clusters with scan statistics
- Probability Inequalities for Sums of Bounded Random Variables
- Probability Inequalities for the Sum of Independent Random Variables
- Probability inequalities for the sum in sampling without replacement
- Remarks on extremal problems in nonparametric curve estimation
- Sharp adaptive estimation of linear functionals.
- Spatial aggregation of local likelihood estimates with applications to classification
- Statistical estimation and optimal recovery
- Test of Significance Based on Wavelet Thresholding and Neyman's Truncation
- Testing goodness-of-fit in regression via order selection criteria
- Uniform and universal Glivenko-Cantelli classes
- Weak convergence and empirical processes. With applications to statistics
Cited in
(3)
This page was built for publication: Optimal calibration for multiple testing against local inhomogeneity in higher dimension
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q639876)
