Uniform change point tests in high dimension

DOI10.1214/15-AOS1347zbMATH Open1327.62467arXiv1511.05333OpenAlexW1820131496MaRDI QIDQ892243FDOQ892243

Authors: Moritz Jirak 

Publication date: 18 November 2015

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

Abstract: Consider $d$ dependent change point tests, each based on a CUSUM-statistic. We provide an asymptotic theory that allows us to deal with the maximum over all test statistics as both the sample size $n$ and $d$ tend to infinity. We achieve this either by a consistent bootstrap or an appropriate limit distribution. This allows for the construction of simultaneous confidence bands for dependent change point tests, and explicitly allows us to determine the location of the change both in time and coordinates in high-dimensional time series. If the underlying data has sample size greater or equal $n$ for each test, our conditions explicitly allow for the large $d$ small $n$ situation, that is, where $n/do0$. The setup for the high-dimensional time series is based on a general weak dependence concept. The conditions are very flexible and include many popular multivariate linear and nonlinear models from the literature, such as ARMA, GARCH and related models. The construction of the tests is completely nonparametric, difficulties associated with parametric model selection, model fitting and parameter estimation are avoided. Among other things, the limit distribution for $ma{x}_{1leqhleqd}su{p}_{0leqtleq1}vertmathcal{W}_{t,h}-tmathcal{W}_{1,h}vert$ is established, where ${mathcal{W}_{t,h}}_{1leqhleqd}$ denotes a sequence of dependent Brownian motions. As an application, we analyze all S&P 500 companies over a period of one year.

Full work available at URL: https://arxiv.org/abs/1511.05333

Recommendations

• Relevant change points in high dimensional time series
• Testing and estimating change-points in the covariance matrix of a high-dimensional time series
• Inference of Breakpoints in High-dimensional Time Series
• On high-dimensional change point problem
• Inference for change points in high-dimensional data via selfnormalization

zbMATH Keywords

extreme value distributionspatial econometricschange point analysishigh-dimensional ARMA/GARCHweakly dependent high-dimensional time series

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Statistics of extreme values; tail inference (62G32) Central limit and other weak theorems (60F05) Interacting random processes; statistical mechanics type models; percolation theory (60K35)

Cites Work

• Time series: theory and methods.
• Multiscale local change point detection with applications to value-at-risk
• Fractionally integrated generalized autoregressive conditional heteroskedasticity
• Title not available (Why is that?)
• Break detection in the covariance structure of multivariate time series models
• Extremes and related properties of random sequences and processes
• Resampling methods for dependent data
• Nonlinear time series. Nonparametric and parametric methods
• The asymptotic distributions of the largest entries of sample correlation matrices.
• Block permutation principles for the change analysis of dependent data
• Asymptotic spectral theory for nonlinear time series
• Structural breaks in time series
• Non-strong mixing autoregressive processes
• Title not available (Why is that?)
• Nonlinear system theory: Another look at dependence
• Change-point detection in panel data
• SLEX Analysis of Multivariate Nonstationary Time Series
• Permutation tests in change point analysis
• A limit theorem for the maximum of normalized sums of independent random variables
• Uniform change point tests in high dimension
• Weakly dependent functional data
• Detection and localization of change-points in high-dimensional network traffic data
• Sequential multi-sensor change-point detection
• A two-sample test for high-dimensional data with applications to gene-set testing
• Covariance and precision matrix estimation for high-dimensional time series
• Asymptotic theory for maximum deviations of sample covariance matrix estimates
• Modelling structural breaks, long memory and stock market volatility: an overview
• Title not available (Why is that?)
• Simultaneous confidence bands for Yule-Walker estimators and order selection
• Testing for change points in time series
• Title not available (Why is that?)
• Limiting laws of coherence of random matrices with applications to testing covariance structure and construction of compressed sensing matrices
• Infinite-dimensional VARs and factor models
• Strict stationarity of generalized autoregressive processes
• Asymptotic results for the empirical process of stationary sequences
• Structural breaks with deterministic and stochastic trends
• On the rate of convergence of normal extremes
• On extreme values in stationary sequences
• Donsker's theorem for self-normalized partial sums processes
• Testing the equality of covariance operators in functional samples
• A central limit theorem for stationary random fields
• Nonmonotonic power for tests of a mean shift in a time series§
• Change-point detection in multichannel and distributed systems
• Testing for changes in the covariance structure of linear processes
• Change-point analysis in increasing dimension
• Darling-Erdős theorem for self-normalized sums
• Berry-Esseen bounds for econometric time series

Cited In (66)

• Efficient multiple change point detection for high‐dimensional generalized linear models
• Change-point detection in high-dimensional covariance structure
• Adaptive Inference for Change Points in High-Dimensional Data
• Detecting structural breaks in realized volatility
• Adaptive Change Point Monitoring for High-Dimensional Data
• Asymptotic distribution-free change-point detection for multivariate and non-Euclidean data
• Relevant change points in high dimensional time series
• Inference for change points in high-dimensional data via selfnormalization
• A robust bootstrap change point test for high-dimensional location parameter
• Group orthogonal greedy algorithm for change-point estimation of multivariate time series
• High dimensional change point estimation via sparse projection
• Change-point testing for parallel data sets with FDR control
• Sequential nonparametric tests for a change in distribution: an application to detecting radiological anomalies
• A likelihood ratio approach to sequential change point detection for a general class of parameters
• Generalized multiple change-point detection in the structure of multivariate, possibly high-dimensional, data sequences
• A computationally efficient and flexible algorithm for high dimensional mean and covariance matrix change point models
• Practical aspects of false alarm control for change point detection: beyond average run length
• Univariate mean change point detection: penalization, CUSUM and optimality
• Fréchet change-point detection
• Robust inference for change points in high dimension
• An empirical-characteristic-function-based change-point test for detection of multiple distributional changes
• High dimensional efficiency with applications to change point tests
• On high-dimensional change point problem
• Monitoring for a change point in a sequence of distributions
• Scalable change-point and anomaly detection in cross-correlated data with an application to condition monitoring
• Sequential change point detection in high dimensional time series
• Change-point inference for high-dimensional heteroscedastic data
• Collective Anomaly Detection in High-Dimensional Var Models
• Minimax rates in sparse, high-dimensional change point detection
• A novel change-point approach for the detection of gas emission sources using remotely contained concentration data
• On change-point estimation under Sobolev sparsity
• Inference on the change point under a high dimensional sparse mean shift
• High-dimensional changepoint detection via a geometrically inspired mapping
• Change-detection-assisted multiple testing for spatiotemporal data
• Inference of Breakpoints in High-dimensional Time Series
• High dimensional change point inference: recent developments and extensions
• Change-point detection in panel data via double CUSUM statistic
• Optimal covariance change point localization in high dimensions
• Multiple change-points detection in high dimension
• Estimation of high-dimensional change-points under a group sparsity structure
• Nonparametric multiple change-point estimation for analyzing large Hi-C data matrices
• Anomaly detection: a functional analysis perspective
• Uniform change point tests in high dimension
• Data-driven selection of the number of change-points via error rate control
• Simultaneous multiple change-point and factor analysis for high-dimensional time series
• Optimal multiple change-point detection for high-dimensional data
• Structural breaks in panel data: large number of panels and short length time series
• A new hybrid approach to panel data change point detection
• Estimating a Change Point in a Sequence of Very High-Dimensional Covariance Matrices
• Change point detection via feedforward neural networks with theoretical guarantees
• Inference in High-Dimensional Online Changepoint Detection
• Mean-Structure and Autocorrelation Consistent Covariance Matrix Estimation
• Detection of multiple change-points in high-dimensional panel data with cross-sectional and temporal dependence
• Detecting Changes in Covariance via Random Matrix Theory
• Activation discovery with FDR control: application to fMRI data
• Change point detection for high dimensional data via kernel measure with application to human aging brain data
• Detection of Multiple Structural Breaks in Large Covariance Matrices
• Detection and estimation of structural breaks in high-dimensional functional time series
• Frequency Detection and Change Point Estimation for Time Series of Complex Oscillation
• Sequential Gaussian approximation for nonstationary time series in high dimensions
• Efficient change point detection and estimation in high-dimensional correlation matrices
• Joint estimation of gradual variance changepoint for panel data with common structures
• \(\ell^2\) inference for change points in high-dimensional time series via a two-way MOSUM
• Dynamic Semiparametric Factor Model With Structural Breaks
• Monitoring Network Changes in Social Media
• Dating the break in high-dimensional data

This page was built for publication: Uniform change point tests in high dimension

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q892243)