Multiscale Quantile Segmentation
From MaRDI portal
Abstract: We introduce a new methodology for analyzing serial data by quantile regression assuming that the underlying quantile function consists of constant segments. The procedure does not rely on any distributional assumption besides serial independence. It is based on a multiscale statistic, which allows to control the (finite sample) probability for selecting the correct number of segments S at a given error level, which serves as a tuning parameter. For a proper choice of this parameter, this tends exponentially fast to the true S, as sample size increases. We further show that the location and size of segments are estimated at minimax optimal rate (compared to a Gaussian setting) up to a log-factor. Thereby, our approach leads to (asymptotically) uniform confidence bands for the entire quantile regression function in a fully nonparametric setup. The procedure is efficiently implemented using dynamic programming techniques with double heap structures, and software is provided. Simulations and data examples from genetic sequencing and ion channel recordings confirm the robustness of the proposed procedure, which at the same hand reliably detects changes in quantiles from arbitrary distributions with precise statistical guarantees.
Recommendations
- Multiscale change-point segmentation: beyond step functions
- Two-stage data segmentation permitting multiscale change points, heavy tails and dependence
- Multiscale change-point segmentation: beyond step functions
- FDR-control in multiscale change-point segmentation
- Segmented model selection in quantile regression using the minimum description length principle
Cites work
- scientific article; zbMATH DE number 3171491 (Why is no real title available?)
- A Modified Bayes Information Criterion with Applications to the Analysis of Comparative Genomic Hybridization Data
- A computationally efficient nonparametric approach for changepoint detection
- A nonparametric approach for multiple change point analysis of multivariate data
- An analysis of variance test for normality (complete samples)
- Asymptotic distribution-free change-point detection for multivariate and non-Euclidean data
- Autocovariance estimation in regression with a discontinuous signal and m-dependent errors: a difference-based approach
- Bump detection in the presence of dependency: does it ease or does it load?
- Change-point detection in multinomial data with a large number of categories
- Change-points: from sequential detection to biology and back
- Changepoint Detection in the Presence of Outliers
- Consistencies and rates of convergence of jump-penalized least squares estimators
- Detection of Multiple Structural Breaks in Multivariate Time Series
- Extensions of smoothing via taut strings
- FDR-control in multiscale change-point segmentation
- Heterogeneous change point inference
- Local extremes, runs, strings and multiresolution. (With discussion)
- Multiple Change-Point Estimation With a Total Variation Penalty
- Multiscale blind source separation
- Multiscale change point inference. With discussion and authors' reply
- Multiscale inference about a density
- Multiscale local change point detection with applications to value-at-risk
- Multiscale testing of qualitative hypotheses
- Multivariate quantiles and multiple-output regression quantiles: from \(L_{1}\) optimization to halfspace depth
- Narrowest-Over-Threshold Detection of Multiple Change Points and Change-Point-Like Features
- New efficient algorithms for multiple change-point detection with reproducing kernels
- New goodness-of-fit tests and their application to nonparametric confidence sets
- Nonparametric maximum likelihood approach to multiple change-point problems
- On estimation of isotonic piecewise constant signals
- Optimal Nonparametric Multivariate Change Point Detection and Localization
- Optimal detection of changepoints with a linear computational cost
- Optimal sparse segment identification with application in copy number variation analysis
- Oracle estimation of a change point in high-dimensional quantile regression
- Piecewise quantile autoregressive modeling for nonstationary time series
- Quantile regression.
- Quantiles for Counts
- Recursive computation of piecewise constant volatilities
- Segmented model selection in quantile regression using the minimum description length principle
- Tail-greedy bottom-up data decompositions and fast multiple change-point detection
- The screening and ranking algorithm to detect DNA copy number variations
- The theory of dynamic programming
- Wild binary segmentation for multiple change-point detection
- \(\ell_1\)-penalized quantile regression in high-dimensional sparse models
Cited in
(8)- Bayesian Change Point Detection with Spike-and-Slab Priors
- Robust Narrowest Significance Pursuit: Inference for Multiple Change-Points in the Median
- Fast and optimal inference for change points in piecewise polynomials via differencing
- Applications of binary segmentation to the estimation of quantal response curves and spatial intensity
- Segmented model selection in quantile regression using the minimum description length principle
- Multiscale scanning with nuisance parameters
- Nonparametric data segmentation in multivariate time series via joint characteristic functions
- Optimal multiple change-point detection for high-dimensional data
This page was built for publication: Multiscale Quantile Segmentation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5881143)
