Directional outlyingness for multivariate functional data
From MaRDI portal
Publication:129235
DOI10.1016/J.CSDA.2018.03.017zbMATH Open1471.62049arXiv1612.04615OpenAlexW2587055720WikidataQ129998490 ScholiaQ129998490MaRDI QIDQ129235FDOQ129235
Wenlin Dai, Wenlin Dai, Marc G. Genton
Publication date: March 2019
Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)
Abstract: The direction of outlyingness is crucial to describing the centrality of multivariate functional data. Motivated by this idea, we generalize classical depth to directional outlyingness for functional data. We investigate theoretical properties of functional directional outlyingness and find that the total outlyingness can be naturally decomposed into two parts: magnitude outlyingness and shape outlyingness which represent the centrality of a curve for magnitude and shape, respectively. Using this decomposition, we provide a visualization tool for the centrality of curves. Furthermore, we design an outlier detection procedure based on functional directional outlyingness. This criterion applies to both univariate and multivariate curves and simulation studies show that it outperforms competing methods. Weather and electrocardiogram data demonstrate the practical application of our proposed framework.
Full work available at URL: https://arxiv.org/abs/1612.04615
Recommendations
outlier detectioncentrality visualizationdirectional outlyingnessmultivariate function dataoutlyingness decomposition
Computational methods for problems pertaining to statistics (62-08) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Functional data analysis (62R10)
Cites Work
- Functional data analysis.
- Nonparametric functional data analysis. Theory and practice.
- Inference for functional data with applications
- Matérn Cross-Covariance Functions for Multivariate Random Fields
- Robust forecasting of mortality and fertility rates: a functional data approach
- Trimmed means for functional data
- Title not available (Why is that?)
- Title not available (Why is that?)
- The multivariate L 1 -median and associated data depth
- On the Concept of Depth for Functional Data
- Global Envelope Tests for Spatial Processes
- Title not available (Why is that?)
- A half-region depth for functional data
- General notions of statistical depth function.
- On a notion of data depth based on random simplices
- On depth measures and dual statistics. A methodology for dealing with general data
- On the use of the bootstrap for estimating functions with functional data
- Projection-based depth functions and associated medians
- Depth-based nonparametric description of functional data, with emphasis on use of spatial depth
- A topologically valid definition of depth for functional data
- Simplicial band depth for multivariate functional data
- The spatial distribution in infinite dimensional spaces and related quantiles and depths
- Weak convergence of discretely observed functional data with applications
- Integrated depth for functional data: statistical properties and consistency
- Equivariance and invariance properties of multivariate quantile and related functions, and the role of standardisation
- Multivariate spatial sign and rank methods
- Title not available (Why is that?)
- A Valid Matérn Class of Cross-Covariance Functions for Multivariate Random Fields With Any Number of Components
- Depth Measures for Multivariate Functional Data
- Consistency of non-integrated depths for functional data
- Multivariate Functional Halfspace Depth
- Multivariate functional outlier detection
- Discussion of ``Multivariate functional outlier detection
- On data depth in infinite dimensional spaces
- Detecting and handling outlying trajectories in irregularly sampled functional datasets
Cited In (30)
- Robust sparse functional regression model
- Two-sample tests for multivariate functional data with applications
- Editorial for the special issue on high-dimensional and functional data analysis
- Functional outlier detection and taxonomy by sequential transformations
- Functional Outlier Detection through Probabilistic Modelling
- An Outlyingness Matrix for Multivariate Functional Data Classification
- Detecting and classifying outliers in big functional data
- Outlier detection in multivariate functional data through a contaminated mixture model
- Depth level set estimation and associated risk measures
- Bivariate Functional Quantile Envelopes With Application to Radiosonde Wind Data
- Review on functional data classification
- Robust smoothed canonical correlation analysis for functional data
- Tests for equality of several covariance matrix functions for multivariate functional data
- Robust functional multivariate analysis of variance with environmental applications
- Elastic Depths for Detecting Shape Anomalies in Functional Data
- Comments on ``Data science, big data and statistics
- Functional Outlier Detection for Density-Valued Data with Application to Robustify Distribution-to-Distribution Regression
- fdaoutlier
- Multivariate Functional Data Visualization and Outlier Detection
- Data adaptive functional outlier detection: analysis of the Paris bike sharing system data
- A Decomposition of Total Variation Depth for Understanding Functional Outliers
- Title not available (Why is that?)
- Sparse Functional Boxplots for Multivariate Curves
- Localization processes for functional data analysis
- Pareto depth for functional data
- Functional boxplots for multivariate curves
- A global test for heteroscedastic one-way FMANOVA with applications
- Trajectory functional boxplots
- Multivariate functional outlier detection using the fast massive unsupervised outlier detection indices
- Level sets of depth measures in abstract spaces
Uses Software
This page was built for publication: Directional outlyingness for multivariate functional data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q129235)
