How the instability of ranks under long memory affects large-sample inference

DOI10.1214/17-STS633zbMATH Open1407.62274MaRDI QIDQ667685FDOQ667685

Authors: Shuyang Bai, Murad S. Taqqu 

Publication date: 1 March 2019

Published in: Statistical Science (Search for Journal in Brave)

Abstract: Under long memory, the limit theorems for normalized sums of random variables typically involve a positive integer called "Hermite rank". There is a different limit for each Hermite rank. From a statistical point of view, however, we argue that a rank other than one is unstable, whereas, a rank equal to one is stable. We provide empirical evidence supporting this argument. This has important consequences. Assuming a higher-order rank when it is not really there usually results in underestimating the order of the fluctuations of the statistic of interest. We illustrate this through various examples involving the sample variance, the empirical processes and the Whittle estimator.

Full work available at URL: https://arxiv.org/abs/1610.00690

Recommendations

• Sensitivity of the Hermite rank
• Sample autocovariances of long-memory time series
• Inference for unstable long-memory processes with applications to fractional unit root autoregressions
• Empirical processes of long-memory sequences
• TESTING FOR LONG MEMORY

zbMATH Keywords

long-range dependencelong memoryinstabilityHermite ranklarge-sample inferencenon-Gaussian limitpower rank

Mathematics Subject Classification ID

Analysis of variance and covariance (ANOVA) (62J10) 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?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A CENTRAL LIMIT THEOREM AND A STRONG MIXING CONDITION
• A central limit theorem for non-instantaneous filters of a stationary Gaussian process
• A central limit theorem for quadratic forms in strongly dependent linear variables and its application to asymptotical normality of Whittle's estimate
• A functional central limit theorem for weakly dependent sequences of random variables
• A new weak dependence condition and applications to moment inequalities
• A noncentral limit theorem for quadratic forms of Gaussian stationary sequences
• A self-normalized approach to confidence interval construction in time series
• A simple test of changes in mean in the possible presence of long-range dependence
• A unified approach to self-normalized block sampling
• AN INTRODUCTION TO LONG-MEMORY TIME SERIES MODELS AND FRACTIONAL DIFFERENCING
• Asymptotic distributions of the sample mean, autocovariances, and autocorrelations of long-memory time series
• Asymptotic properties of \(U\)-processes under long-range dependence
• Bivariate symmetric statistics of long-range dependent observations
• Block sampling under strong dependence
• Central limit theorems for non-linear functionals of Gaussian fields
• Convergence of integrated processes of arbitrary Hermite rank
• Covariances estimation for long-memory processes
• Density estimation under long-range dependence
• ESTIMATORS FOR LONG-RANGE DEPENDENCE: AN EMPIRICAL STUDY
• Estimators of long-memory: Fourier versus wavelets
• Gaussian Hilbert Spaces
• Gaussian semiparametric estimation of long range dependence
• Kernel density estimation for linear processes
• Large sample inference for long memory processes
• Large scale behavior of wavelet coefficients of non-linear subordinated processes with long memory
• Large-sample properties of parameter estimates for strongly dependent stationary Gaussian time series
• Limit theorems for functionals of moving averages
• Limit theorems for nonlinear functionals of a stationary Gaussian sequence of vectors
• Local linear regression estimation for time series with long-range dependence
• Long-Range Dependence and Self-Similarity
• Long-memory processes. Probabilistic properties and statistical methods
• Long-range dependence and Appell rank
• Long-range dependence and the rank of decompositions
• M Estimators of Location for Gaussian and Related Processes With Slowly Decaying Serial Correlations
• MULTIVARIATE LIMIT THEOREMS IN THE CONTEXT OF LONG‐RANGE DEPENDENCE
• Multiple Wiener-Itô integrals. With applications to limit theorems
• NON‐PARAMETRIC ESTIMATION WITH STRONGLY DEPENDENT MULTIVARIATE TIME SERIES
• Necessary conditions for nonlinear functionals of Gaussian processes to satisfy central limit theorems
• Non-central limit theorems for non-linear functional of Gaussian fields
• Non-central limit theorems for non-linear functionals of \(k\) Gaussian fields
• Non-parametric change-point tests for long-range dependent data
• Noncentral limit theorems and Appell polynomials
• Nonlinear system theory: Another look at dependence
• Nonparametric regression with heteroscedastic long memory errors
• On Berry-Esseen bounds for non-instantaneous filters of linear processes
• On bilinear forms in Gaussian random variables and Toeplitz matrices
• On central and non-central limit theorems in density estimation for sequences of long-range dependence
• On inference based on the one-sample sign statistic for long-range dependent data
• On spline regression under Gaussian subordination with long memory
• On the validity of resampling methods under long memory
• Random-design regression under long-range dependent errors
• Ratio test for variance change point in linear process with long memory
• Regression model fitting with long memory errors
• Regularization and integral representations of Hermite processes
• Robust estimation of the scale and of the autocovariance function of Gaussian short- and long-range dependent processes
• Robustness of whittle-type estimators for time series with long-range dependence
• Sensitivity of the Hermite rank
• Slowly Decaying Correlations, Testing Normality, Nuisance Parameters
• Some Limit Theorems for Stationary Processes
• Stochastic processes and long range dependence
• Subsampling for General Statistics under Long Range Dependence with application to change point analysis
• Subsampling inference for the mean of heavy-tailed long-memory time series
• The empirical process of some long-range dependent sequences with an application to U-statistics
• The smoothing dichotomy in nonparametric regression under long‐memory errors
• Time series: theory and methods.
• Towards a unified asymptotic theory for autoregression
• UNIT ROOT TESTING FOR FUNCTIONALS OF LINEAR PROCESSES
• VALIDITY OF THE SAMPLING WINDOW METHOD FOR LONG-RANGE DEPENDENT LINEAR PROCESSES
• Wavelet estimation of the long memory parameter for Hermite polynomial of Gaussian processes
• Weak convergence to fractional brownian motion and to the rosenblatt process
• Whittle estimator for finite-variance non-Gaussian time series with long memory
• Zones of attraction of self-similar multiple integrals

Cited In (11)

• Note on asymptotic behavior of spatial sign autocovariance matrices
• When scattering transform meets non-Gaussian random processes, a double scaling limit result
• On operator fractional Lévy motion: integral representations and time-reversibility
• On optimal block resampling for Gaussian-subordinated long-range dependent processes
• Sensitivity of the Hermite rank
• Representations of Hermite processes using local time of intersecting stationary stable regenerative sets
• Comparing the marginal densities of two strictly stationary linear processes
• Wavelet eigenvalue regression in high dimensions
• Reduction principle for functionals of strong-weak dependent vector random fields
• Two-step wavelet-based estimation for Gaussian mixed fractional processes
• Asymptotic theory for the detection of mixing in anomalous diffusion

Uses Software

• longmemo

This page was built for publication: How the instability of ranks under long memory affects large-sample inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q667685)