The two-sample problem for Poisson processes: adaptive tests with a nonasymptotic wild bootstrap approach

DOI10.1214/13-AOS1114zbMATH Open1273.62102arXiv1203.3572WikidataQ105584284 ScholiaQ105584284MaRDI QIDQ366986FDOQ366986

Authors: Magalie Fromont, Béatrice Laurent, P. Reynaud-Bouret 

Publication date: 25 September 2013

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

Abstract: Considering two independent Poisson processes, we address the question of testing equality of their respective intensities. We first propose single tests whose test statistics are U-statistics based on general kernel functions. The corresponding critical values are constructed from a non-asymptotic wild bootstrap approach, leading to level alpha tests. Various choices for the kernel functions are possible, including projection, approximation or reproducing kernels. In this last case, we obtain a parametric rate of testing for a weak metric defined in the RKHS associated with the considered reproducing kernel. Then we introduce, in the other cases, an aggregation procedure, which allows us to import ideas coming from model selection, thresholding and/or approximation kernels adaptive estimation. The resulting multiple tests are proved to be of level alpha, and to satisfy non-asymptotic oracle type conditions for the classical L2-norm. From these conditions, we deduce that they are adaptive in the minimax sense over a large variety of classes of alternatives based on classical and weak Besov bodies in the univariate case, but also Sobolev and anisotropic Nikol'skii-Besov balls in the multivariate case.

Full work available at URL: https://arxiv.org/abs/1203.3572

Recommendations

• Adaptive tests of homogeneity for a Poisson process
• Nonparametric hypothesis testing for intensity of the Poisson process
• Testing of two sample proportional intensity assumption for non-homogeneous Poisson processes
• Tests for Monotonic Intensity in a Poisson Process
• GOODNESS-OF-FIT TESTING FOR TWO-DIMENSIONAL POISSON PROCESSES WITH DISCONTINUOUS INTENSITY FUNCTION

zbMATH Keywords

bootstrapkernel methodsminimax separation ratesadaptive testsaggregation methodsmultiple kernel

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Asymptotic properties of nonparametric inference (62G20) Monte Carlo methods (65C05) Point processes (e.g., Poisson, Cox, Hawkes processes) (60G55) Nonparametric statistical resampling methods (62G09) Markov processes: hypothesis testing (62M02) Applications of functional analysis in probability theory and statistics (46N30)

Cites Work

• Bootstrap methods: another look at the jackknife
• Bootstrap and randomization tests of some nonparametric hypotheses
• A Bootstrap Revival of Some Nonparametric Distance Tests
• Title not available (Why is that?)
• On the bootstrap of \(U\) and \(V\) statistics
• Bootstrap, wild bootstrap, and asymptotic normality
• Exchangeably weighted bootstraps of the general empirical process
• Adaptive hypothesis testing using wavelets
• An Adaptive, Rate-Optimal Test of a Parametric Mean-Regression Model Against a Nonparametric Alternative
• Universality, Characteristic Kernels and RKHS Embedding of Measures
• Title not available (Why is that?)
• The Large-Sample Power of Tests Based on Permutations of Observations
• Introduction to nonparametric estimation
• Sparsity in multiple kernel learning
• Non-asymptotic minimax rates of testing in signal detection
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Consistency of the group Lasso and multiple kernel learning
• Title not available (Why is that?)
• Linear and convex aggregation of density estimators
• Exact and Approximate Stepdown Methods for Multiple Hypothesis Testing
• How do bootstrap and permutation tests work?
• Learning the kernel matrix with semidefinite programming
• Title not available (Why is that?)
• The Logic of Inductive Inference
• An Introduction to the Theory of Point Processes
• Bandwidth selection in kernel density estimation: oracle inequalities and adaptive minimax optimality
• Learning the kernel function via regularization
• Choosing multiple parameters for support vector machines
• Weighted bootstrapping of \(U\)-statistics
• Rademacher penalties and structural risk minimization
• Nonparametric homogeneity tests
• Invariant tests for uniformity on compact Riemannian manifolds based on Sobolev norms
• A more powerful test for comparing two Poisson means
• Homogeneity tests for several Poisson populations
• Permutation tests for directional data
• Consistency of the generalized bootstrap for degenerate \(U\)-statistics
• Asymptotically minimax hypothesis testing for nonparametric alternatives. III
• Adaptive tests of linear hypotheses by model selection
• A comparative study of tests for the difference of two Poisson means
• Testing of two sample proportional intensity assumption for non-homogeneous Poisson processes
• Random quadratic forms and the bootstrap for \(U\)-statistics
• Adaptive chi-square tests
• Adaptive and spatially adaptive testing of a nonparametric hypothesis.
• Estimation and detection of functions from anisotropic Sobolev classes
• Global uniform risk bounds for wavelet deconvolution estimators
• Title not available (Why is that?)
• Parametric bootstrap and approximate tests for two Poisson variates
• The two-sample problem for Poisson processes: adaptive tests with a nonasymptotic wild bootstrap approach
• On comparing two poisson intensity functions
• Experiment Size and Power Comparisons for Two-Sample Poisson Tests
• Tail and moment estimates for some types of chaos
• Power Computations for Designing Comparative Poisson Trials
• Testing the hypothesis of proportional hazards in two populations
• SOME SIMPLE APPROXIMATE TESTS FOR POISSON VARIATES
• Model selection and error estimation
• Adaptive tests of homogeneity for a Poisson process
• Nonparametric hypothesis testing for intensity of the Poisson process

Cited In (13)

• Exponential inequality for chaos based on sampling without replacement
• Adaptive test of independence based on HSIC measures
• Concentration inequalities, counting processes and adaptive statistics
• Minimax optimality of permutation tests
• Chi-squared test for hypothesis testing of homogeneity
• Minimax and adaptive tests for detecting abrupt and possibly transitory changes in a Poisson process
• Title not available (Why is that?)
• On normal approximations for the two-sample problem on multidimensional tori
• Parametric bootstrap and approximate tests for two Poisson variates
• A model of Poissonian interactions and detection of dependence
• The two-sample problem for Poisson processes: adaptive tests with a nonasymptotic wild bootstrap approach
• Adaptive tests of homogeneity for a Poisson process
• Bootstrap and permutation tests of independence for point processes

This page was built for publication: The two-sample problem for Poisson processes: adaptive tests with a nonasymptotic wild bootstrap approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q366986)