Fréchet change-point detection
From MaRDI portal
Publication:1996771
DOI10.1214/19-AOS1930zbMATH Open1461.62243arXiv1911.11864MaRDI QIDQ1996771FDOQ1996771
Authors: Paromita Dubey, Hans-Georg Müller 
Publication date: 26 February 2021
Published in: The Annals of Statistics (Search for Journal in Brave)
Abstract: We propose a method to infer the presence and location of change-points in the distribution of a sequence of independent data taking values in a general metric space, where change-points are viewed as locations at which the distribution of the data sequence changes abruptly in terms of either its Fr'echet mean or Fr'echet variance or both. The proposed method is based on comparisons of Fr'echet variances before and after putative change-point locations and does not require a tuning parameter except for the specification of cut-off intervals near the endpoints where change-points are assumed not to occur. Our results include theoretical guarantees for consistency of the test under contiguous alternatives when a change-point exists and also for consistency of the estimated location of the change-point if it exists, where under the null hypothesis of no change-point the limit distribution of the proposed scan function is the square of a standardized Brownian Bridge. These consistency results are applicable for a broad class of metric spaces under mild entropy conditions. Examples include the space of univariate probability distributions and the space of graph Laplacians for networks. Simulation studies demonstrate the effectiveness of the proposed methods, both for inferring the presence of a change-point and estimating its location. We also develop theory that justifies bootstrap-based inference and illustrate the new approach with sequences of maternal fertility distributions and communication networks.
Full work available at URL: https://arxiv.org/abs/1911.11864
Recommendations
bootstrapempirical processesrandom objectsmetric spaceBrownian bridgegraph Laplaciansdynamics of networksobject datarandom densities
Nonparametric hypothesis testing (62G10) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Applications of statistics to biology and medical sciences; meta analysis (62P10) Measures of association (correlation, canonical correlation, etc.) (62H20) Statistics on metric spaces (62R20)
Cites Work
- Weak convergence and empirical processes. With applications to statistics
- Fréchet regression for random objects with Euclidean predictors
- Consistent change-point detection with kernels
- Asymptotic distribution-free change-point detection for multivariate and non-Euclidean data
- Multiple change-point detection: a selective overview
- Graph-based change-point detection
- Emergence of Scaling in Random Networks
- Parametric statistical change point analysis. With applications to genetics, medicine, and finance
- Title not available (Why is that?)
- High dimensional change point estimation via sparse projection
- A nonparametric approach for multiple change point analysis of multivariate data
- Fréchet analysis of variance for random objects
- Title not available (Why is that?)
- A Kernel Multiple Change-point Algorithm via Model Selection
- Uniform change point tests in high dimension
- Homogeneity and change-point detection tests for multivariate data using rank statistics
- Hypothesis testing for network data in functional neuroimaging
- On the geometry of metric measure spaces. I
- Likelihood Ratio Tests for a Change in the Multivariate Normal Mean
- Title not available (Why is that?)
- Estimating the Current Mean of a Normal Distribution which is Subjected to Changes in Time
- A central limit theorem under metric entropy with \(L_ 2\) bracketing
- Covering Numbers for Convex Functions
- Tests for a change-point
- A remark on approximate \(M\)-estimators
- Confidence Sets in Change-Point Problems
- A comparison inequality for sums of independent random variables
- Geodesic PCA versus Log-PCA of Histograms in the Wasserstein Space
- Tests for change of parameter at unknown times and distributions of some related functionals on Brownian motion
- Title not available (Why is that?)
- Wasserstein covariance for multiple random densities
- Title not available (Why is that?)
- Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics
- A Spatial Modeling Approach for Linguistic Object Data: Analyzing Dialect Sound Variations Across Great Britain
Cited In (20)
- Consistent change-point detection with kernels
- Asymptotic distribution-free change-point detection for multivariate and non-Euclidean data
- Total variation regularized Fréchet regression for metric-space valued data
- A novel dual-criterion framework for change point detection
- Homogeneity tests of covariance for high-dimensional functional data with applications to event segmentation
- Joint modeling of change-point identification and dependent dynamic community detection
- Monitoring for a change point in a sequence of distributions
- Break point detection for functional covariance
- Medoid splits for efficient random forests in metric spaces
- Functional Outlier Detection for Density-Valued Data with Application to Robustify Distribution-to-Distribution Regression
- Two-sample and change-point inference for non-Euclidean valued time series
- Dimension Reduction for Fréchet Regression
- FDR-control in multiscale change-point segmentation
- Logarithmic method of moments estimators for the Fréchet distribution
- Detection and localization of changes in a panel of densities
- The Fréchet mean of inhomogeneous random graphs
- Change‐Point Estimation of Fractionally Integrated Processes
- Determining the number of change-point via high-dimensional cross-validation
- Gradual variance change point detection with a smoothly changing mean trend
- Metric statistics: exploration and inference for random objects with distance profiles
This page was built for publication: Fréchet change-point detection
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1996771)
