ECA: High-Dimensional Elliptical Component Analysis in Non-Gaussian Distributions
From MaRDI portal
Abstract: We present a robust alternative to principal component analysis (PCA) --- called elliptical component analysis (ECA) --- for analyzing high dimensional, elliptically distributed data. ECA estimates the eigenspace of the covariance matrix of the elliptical data. To cope with heavy-tailed elliptical distributions, a multivariate rank statistic is exploited. At the model-level, we consider two settings: either that the leading eigenvectors of the covariance matrix are non-sparse or that they are sparse. Methodologically, we propose ECA procedures for both non-sparse and sparse settings. Theoretically, we provide both non-asymptotic and asymptotic analyses quantifying the theoretical performances of ECA. In the non-sparse setting, we show that ECA's performance is highly related to the effective rank of the covariance matrix. In the sparse setting, the results are twofold: (i) We show that the sparse ECA estimator based on a combinatoric program attains the optimal rate of convergence; (ii) Based on some recent developments in estimating sparse leading eigenvectors, we show that a computationally efficient sparse ECA estimator attains the optimal rate of convergence under a suboptimal scaling.
Recommendations
- ePCA: high dimensional exponential family PCA
- An Expectation-Maximization Approach to Nonlinear Component Analysis
- Euler principal component analysis
- Statistical methods generalizing principal component analysis to non-Euclidean spaces
- Principal component analysis in very high-dimensional spaces
- PCA Consistency for Non-Gaussian Data in High Dimension, Low Sample Size Context
- Semiparametric estimation of the high-dimensional elliptical distribution
- Noncircular Principal Component Analysis and Its Application to Model Selection
- Non-Gaussian component analysis using entropy methods
Cites work
- A Direct Formulation for Sparse PCA Using Semidefinite Programming
- A distribution-free M-estimator of multivariate scatter
- A multivariate version of kendall's τ
- A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis
- Adaptive estimation of the copula correlation matrix for semiparametric elliptical copulas
- Affine-invariant aligned rank tests for the multivariate general linear model with VARMA errors
- An introduction to random matrices
- CODA: high dimensional copula discriminant analysis
- Computational barriers in minimax submatrix detection
- Efficient R-estimation of principal and common principal components
- Generalized power method for sparse principal component analysis
- High dimensional covariance matrix estimation using a factor model
- High-dimensional analysis of semidefinite relaxations for sparse principal components
- High-dimensional covariance matrix estimation with missing observations
- High-dimensional rank tests for sphericity
- scientific article; zbMATH DE number 45785 (Why is no real title available?)
- scientific article; zbMATH DE number 1350311 (Why is no real title available?)
- scientific article; zbMATH DE number 5200028 (Why is no real title available?)
- Minimax sparse principal subspace estimation in high dimensions
- Multivariate extremes, aggregation and dependence in elliptical distributions
- Multivariate nonparametric methods with R. An approach based on spatial signs and ranks.
- Multivariate nonparametric tests
- On consistency and sparsity for principal components analysis in high dimensions
- On the sample covariance matrix estimator of reduced effective rank population matrices, with applications to fPCA
- On the Sum of the Largest Eigenvalues of a Symmetric Matrix
- On Tyler's M-functional of scatter in high dimension
- Optimal detection of sparse principal components in high dimension
- Optimal estimation and rank detection for sparse spiked covariance matrices
- Optimal procedures based on interdirections and pseudo-Mahalanobis ranks for testing multivariate elliptic white noise against ARMA dependence
- Optimal rank-based testing for principal components
- Optimal signed-rank tests based on hyperplanes
- Optimal tests for multivariate location based on interdirections and pseudo-Mahalanobis ranks.
- Perturbation bounds in connection with singular value decomposition
- Radial estimates and the test for sphericity
- Rank-based optimal tests of the adequacy of an elliptic VARMA model
- Regularized estimation of large covariance matrices
- Robust singular value decomposition analysis of microarray data
- Robustifying principal component analysis with spatial sign vectors
- Scale-invariant sparse PCA on high-dimensional meta-elliptical data
- Semiparametrically efficient rank-based inference for shape. I: optimal rank-based tests for sphericity
- Semiparametrically efficient rank-based inference for shape. II: Optimal \(R\)-estimation of shape
- Sign and rank covariance matrices
- Sign test of independence between two random vectors.
- Some robust estimates of principal components
- Sparse principal component analysis and iterative thresholding
- Sparse principal component analysis via regularized low rank matrix approximation
- Sparse principal component analysis with missing observations
- Statistical analysis of latent generalized correlation matrix estimation in transelliptical distribution
- Statistical Tools for Finance and Insurance
- Symmetrised M-estimators of multivariate scatter
- The Rotation of Eigenvectors by a Perturbation. III
- The statistical analysis of fMRI data
- Truncated power method for sparse eigenvalue problems
- User-friendly tail bounds for sums of random matrices
Cited in
(32)- Robust functional principal component analysis for non-Gaussian longitudinal data
- ePCA: high dimensional exponential family PCA
- Robust covariance and scatter matrix estimation under Huber's contamination model
- Robust factor number specification for large-dimensional elliptical factor model
- On universally consistent and fully distribution-free rank tests of vector independence
- A literature review of (Sparse) exponential family PCA
- Robust covariance estimation for distributed principal component analysis
- Robust sufficient dimension reduction via ball covariance
- Large covariance estimation through elliptical factor models
- Scale-invariant sparse PCA on high-dimensional meta-elliptical data
- An overview of heavy-tail extensions of multivariate Gaussian distribution and their relations
- Functional principal component analysis estimator for non-Gaussian data
- High-dimensional proportionality test of two covariance matrices and its application to gene expression data
- Robust Functional Principal Component Analysis via a Functional Pairwise Spatial Sign Operator
- Robust tests for scatter separability beyond Gaussianity
- Robustness of principal component analysis with Spearman's rank matrix
- Large-Dimensional Factor Analysis Without Moment Constraints
- High-Dimensional Elliptical Sliced Inverse Regression in Non-Gaussian Distributions
- Identifying the Structure of High-Dimensional Time Series via Eigen-Analysis
- Robust functional principal component analysis for non-Euclidean random objects
- A new non-parametric Kendall's tau for matrix-valued elliptical observations
- Concentration and consistency of sample covariance matrix functionals in sub-Gaussian models
- Robust direction estimation in single-index models via cumulative divergence
- Functional sufficient dimension reduction through distance covariance
- Distributed Learning for Principal Eigenspaces without Moment Constraints
- High dimensional T-type estimator for robust covariance matrix estimation with applications to elliptical factor models
- Robust estimation of functional factor models with functional pairwise spatial signs
- Non-independent component analysis
- Robust inverse regression for multivariate elliptical functional data
- Tail-robust factor modelling of vector and tensor time series in high dimensions
- Sufficient dimension reduction via inverse conditional mean or variance independence
- Moment bounds for large autocovariance matrices under dependence
This page was built for publication: ECA: High-Dimensional Elliptical Component Analysis in Non-Gaussian Distributions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4690955)
