A distribution free test for changes in the trend function of locally stationary processes

DOI10.1214/21-EJS1871zbMATH Open1476.62079arXiv2005.11132OpenAlexW3186230236MaRDI QIDQ2233554FDOQ2233554

Holger Dette, Florian Heinrichs

Publication date: 11 October 2021

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

Abstract: In the common time series model $X_{i,n}=mu(i/n)+varepsilo{n}_{i,n}$ with non-stationary errors we consider the problem of detecting a significant deviation of the mean function $mu$ from a benchmark $g(mu)$ (such as the initial value $mu(0)$ or the average trend $in{t}_0^{1}mu(t)dt$). The problem is motivated by a more realistic modelling of change point analysis, where one is interested in identifying relevant deviations in a smoothly varying sequence of means $(mu(i/n){)}_{i=1,ldots,n}$ and cannot assume that the sequence is piecewise constant. A test for this type of hypotheses is developed using an appropriate estimator for the integrated squared deviation of the mean function and the threshold. By a new concept of self-normalization adapted to non-stationary processes an asymptotically pivotal test for the hypothesis of a relevant deviation is constructed. The results are illustrated by means of a simulation study and a data example.

Full work available at URL: https://arxiv.org/abs/2005.11132

Recommendations

• Detecting relevant changes in the mean of nonstationary processes -- a mass excess approach
• Are deviations in a gradually varying mean relevant? A testing approach based on sup-norm estimators
• scientific article; zbMATH DE number 2154633
• Detecting deviations from second-order stationarity in locally stationary functional time series
• Testing for autocovariances changes in time series models with nonparametric trends

zbMATH Keywords

nonparametric regressionchange point analysislocal stationary processes

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Nonparametric hypothesis testing (62G10) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Stationary stochastic processes (60G10)

Cites Work

• Tail-greedy bottom-up data decompositions and fast multiple change-point detection
• Weak convergence and empirical processes. With applications to statistics
• Detecting relevant changes in the mean of nonstationary processes -- a mass excess approach
• Title not available (Why is that?)
• Structural breaks in time series
• Gaussian approximations for non-stationary multiple time series
• Multiscale change point detection for dependent data
• Greedy Kernel Change-Point Detection
• Narrowest-Over-Threshold Detection of Multiple Change Points and Change-Point-Like Features
• Title not available (Why is that?)
• Multiscale Change Point Inference
• A Self-Normalized Approach to Confidence Interval Construction in Time Series
• Self-Normalization for Time Series: A Review of Recent Developments
• Inference for single and multiple change-points in time series
• Banding sample autocovariance matrices of stationary processes
• Heteroscedasticity and Autocorrelation Robust Structural Change Detection
• Local linear quantile estimation for nonstationary time series
• Quantile spectral processes: asymptotic analysis and inference
• Improvement of Kernel Type Density Estimators
• Testing for changes in multivariate dependent observations with an application to temperature changes
• Beyond Parametrics in Interdisciplinary Research: Festschrift in Honor of Professor Pranab K. Sen
• Nonparametric statistical procedures for the changepoint problem
• Inference for modulated stationary processes
• Change Point Analysis of Correlation in Non-stationary Time Series
• Analysis of Non‐Stationary Modulated Time Series with Applications to Oceanographic Surface Flow Measurements

Cited In (3)

• Detecting changes in the trend function of heteroscedastic time series
• Distribution-free three- sample test for detecting trend in the pure location model
• Asymptotic null distributions of stationarity and nonstationarity tests under local-to-finite variance errors

Uses Software

• ElemStatLearn
• breakfast

This page was built for publication: A distribution free test for changes in the trend function of locally stationary processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2233554)