Changepoint Detection in the Presence of Outliers
From MaRDI portal
Publication:5229902
Abstract: Many traditional methods for identifying changepoints can struggle in the presence of outliers, or when the noise is heavy-tailed. Often they will infer additional changepoints in order to fit the outliers. To overcome this problem, data often needs to be pre-processed to remove outliers, though this is difficult for applications where the data needs to be analysed online. We present an approach to changepoint detection that is robust to the presence of outliers. The idea is to adapt existing penalised cost approaches for detecting changes so that they use loss functions that are less sensitive to outliers. We argue that loss functions that are bounded, such as the classical biweight loss, are particularly suitable -- as we show that only bounded loss functions are robust to arbitrarily extreme outliers. We present an efficient dynamic programming algorithm that can find the optimal segmentation under our penalised cost criteria. Importantly, this algorithm can be used in settings where the data needs to be analysed online. We show that we can consistently estimate the number of changepoints, and accurately estimate their locations, using the biweight loss function. We demonstrate the usefulness of our approach for applications such as analysing well-log data, detecting copy number variation, and detecting tampering of wireless devices.
Recommendations
- scientific article; zbMATH DE number 1916873
- A robust changepoint detection method
- Detecting change-points in extremes
- Change Point Detection in a General Class of Distributions
- Detection of change points: a survey of methodologies
- Changepoint detection in non-exchangeable data
- Outlier-resistant algorithms for detecting a change in a stochastic process
Cites work
- A computationally efficient nonparametric approach for changepoint detection
- A pairwise likelihood-based approach for changepoint detection in multivariate time series models
- A pruned dynamic programming algorithm to recover the best segmentations with 1 to \(K_{\max}\) change-points
- An exact approach to Bayesian sequential change point detection
- Approximate simulation-free Bayesian inference for multiple changepoint models with dependence within segments
- Bootstrap in detection of changes in linear regression
- Changepoint estimation: another look at multiple testing problems
- Circular binary segmentation for the analysis of array-based DNA copy number data
- CONTINUOUS INSPECTION SCHEMES
- Estimation of a noisy discrete-time step function: Bayes and empirical Bayes approaches
- scientific article; zbMATH DE number 4169866 (Why is no real title available?)
- Inference about the change-point from cumulative sum tests
- International encyclopedia of statistical science.
- Least-squares estimation of an unknown number of shifts in a time series
- M-procedures for detection of changes for dependent observations
- Multiscale change point inference. With discussion and authors' reply
- Numerical Bayesian Methods Applied to Signal Processing
- On optimal multiple changepoint algorithms for large data
- On the Likelihood Ratio Test for a Shift in Location of Normal Populations
- Optimal detection of changepoints with a linear computational cost
- Wild binary segmentation for multiple change-point detection
Cited in
(44)- Real Time Anomaly Detection And Categorisation
- Robust algorithms for multiphase regression models
- Most recent changepoint detection in censored panel data
- Is a finite intersection of balls covered by a finite union of balls in Euclidean spaces?
- Sequential change point test in the presence of outliers: the density power divergence based approach
- Monitoring procedures for strict stationarity based on the multivariate characteristic function
- Consistency of a range of penalised cost approaches for detecting multiple changepoints
- Changepoint detection in non-exchangeable data
- Scalable change-point and anomaly detection in cross-correlated data with an application to condition monitoring
- Parallelization of a Common Changepoint Detection Method
- scientific article; zbMATH DE number 2147392 (Why is no real title available?)
- Graphical Influence Diagnostics for Changepoint Models
- Alternating Pruned Dynamic Programming for Multiple Epidemic Change-Point Estimation
- Rank-based multiple change-point detection
- Subset Multivariate Collective and Point Anomaly Detection
- Robust change detection for large-scale data streams
- BOOTSTRAP INFERENCE FOR MULTIPLE CHANGE-POINTS IN TIME SERIES
- On optimal segmentation and parameter tuning for multiple change-point detection and inference
- Multiscale Quantile Segmentation
- Multipartition model for multiple change point identification
- Scalable Bayesian Multiple Changepoint Detection via Auxiliary Uniformisation
- Detecting Abrupt Changes in the Presence of Local Fluctuations and Autocorrelated Noise
- Loss function-based change point detection in risk measures
- Bayesian Change Point Detection with Spike-and-Slab Priors
- Relating and comparing methods for detecting changes in mean
- Sequential change-point detection: computation versus statistical performance
- Detecting changes in the transmission rate of a stochastic epidemic model
- Most Recent Changepoint Detection in Panel Data
- Scalable multiple changepoint detection for functional data sequences
- Bayesian multiple changepoint detection with missing data and its application to the magnitude-frequency distributions
- Cross-validation for change-point regression: pitfalls and solutions
- Multiple change-point detection for regression curves
- A Composite Likelihood-Based Approach for Change-Point Detection in Spatio-Temporal Processes
- Bayesian multiple change point detection in the presence of outliers and its application to the magnitude-frequency distributions
- A latent variable model with change-points and its application to time pressure effects in educational assessment
- Trend and Variance Adaptive Bayesian Changepoint Analysis and Local Outlier Scoring
- Drift versus Shift: Decoupling Trends and Changepoint Analysis
- A robust and efficient change point detection method for high-dimensional linear models
- Robust multi-task regression with shifting low-rank patterns
- Assessing distance measures for change point detection in continual learning scenarios
- Improving power by conditioning on less in post-selection inference for changepoints
- Simultaneous detection of structural breaks and outliers in time series
- Localising change points in piecewise polynomials of general degrees
- Optimal nonparametric change point analysis
This page was built for publication: Changepoint Detection in the Presence of Outliers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5229902)
