On inference validity of weighted U-statistics under data heterogeneity

DOI10.1214/18-EJS1462zbMATH Open1402.62023OpenAlexW2964338663WikidataQ129308494 ScholiaQ129308494MaRDI QIDQ1786572FDOQ1786572

Authors: Fang Han, Tianchen Qian 

Publication date: 24 September 2018

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

Abstract: Motivated by challenges on studying a new correlation measurement being popularized in evaluating online ranking algorithms' performance, this manuscript explores the validity of uncertainty assessment for weighted U-statistics. Without any commonly adopted assumption, we verify Efron's bootstrap and a new resampling procedure's inference validity. Specifically, in its full generality, our theory allows both kernels and weights asymmetric and data points not identically distributed, which are all new issues that historically have not been addressed. For achieving strict generalization, for example, we have to carefully control the order of the "degenerate" term in U-statistics which are no longer degenerate under the empirical measure for non-i.i.d. data. Our result applies to the motivating task, giving the region at which solid statistical inference can be made.

Full work available at URL: https://arxiv.org/abs/1804.00034

Recommendations

• On the asymptotic behavior of weighted \(U\)-statistics
• On the asymptotic behavior of weighted \(U\)-statistics
• Weighted U-statistics for likelihood-ratio ordering of bivariate data
• Assessing the validity of weighted generalized estimating equations
• A U-statistic-based test of treatment effect heterogeneity
• Weighted approximations for Studentized \(U\)-statistics
• Weighted bootstrapping of \(U\)-statistics

zbMATH Keywords

bootstrapconsistencycentral limit theoremrank correlationweighted U-statisticsaverage-precision correlation

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Asymptotic distribution theory in statistics (62E20) Nonparametric statistical resampling methods (62G09) Central limit and other weak theorems (60F05)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Class of Statistics with Asymptotically Normal Distribution
• A NEW MEASURE OF RANK CORRELATION
• Approximation Theorems of Mathematical Statistics
• Asymptotic distributions for weighted \(U\)-statistics
• Asymptotic distributions of weighted \(U\)-statistics of degree 2
• Asymptotic normality of permutation statistics derived from weighted sums of bivariate functions
• Asymptotics of randomly weighted image- and image-statistics: application to bootstrap
• Bootstrap methods: another look at the jackknife
• Bootstrap procedures under some non-i.i.d. models
• Bootstrapping locally stationary processes
• Central limit theorem and the bootstrap for \(U\)-statistics of strongly mixing data
• Convergence rates for U-statistics and related statistics
• Estimates of the Regression Coefficient Based on Kendall's Tau
• Fitting time series models to nonstationary processes
• Heavy-Tail Phenomena
• Inference of weighted \(V\)-statistics for nonstationary time series and its applications
• Large sample confidence regions based on subsamples under minimal assumptions
• Limiting behavior of U-statistics for stationary, absolutely regular processes
• Local block bootstrap
• Matched-block bootstrap for dependent data
• On the asymptotic behavior of weighted \(U\)-statistics
• On the moving block bootstrap under long range dependence
• On weighted \(U\)-statistics for stationary processes.
• Some asymptotic theory for the bootstrap
• Subsampling
• THE BOOTSTRAP OF THE MEAN FOR DEPENDENT HETEROGENEOUS ARRAYS
• Tapered block bootstrap
• The bootstrap and Edgeworth expansion
• The dependent wild bootstrap
• The jackknife and the bootstrap for general stationary observations
• The moving blocks bootstrap and robust inference for linear least squares and quantile regressions
• Using i.i.d. bootstrap inference for general non-i.i.d. models
• When does bootstrap work! Asymptotic results and simulations

Cited In (7)

• Kendall's tau-based inference for gradually changing dependence structures
• Asymptotic normality for -dependent and constrained -statistics, with applications to pattern matching in random strings and permutations
• Assessing the validity of weighted generalized estimating equations
• Quasi \(U\)-statistics of infinite order and applications to the subgroup decomposition of some diversity measures
• Weak convergence of the conditional U-statistics for locally stationary functional time series
• Concentration inequality for U-statistics of order two for uniformly ergodic Markov chains
• Limit theorems for a class of processes generalizing the U -empirical process

This page was built for publication: On inference validity of weighted U-statistics under data heterogeneity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1786572)