The minimum regularized covariance determinant estimator
From MaRDI portal
Abstract: The Minimum Covariance Determinant (MCD) approach robustly estimates the location and scatter matrix using the subset of given size with lowest sample covariance determinant. Its main drawback is that it cannot be applied when the dimension exceeds the subset size. We propose the Minimum Regularized Covariance Determinant (MRCD) approach, which differs from the MCD in that the scatter matrix is a convex combination of a target matrix and the sample covariance matrix of the subset. A data-driven procedure sets the weight of the target matrix, so that the regularization is only used when needed. The MRCD estimator is defined in any dimension, is well-conditioned by construction and preserves the good robustness properties of the MCD. We prove that so-called concentration steps can be performed to reduce the MRCD objective function, and we exploit this fact to construct a fast algorithm. We verify the accuracy and robustness of the MRCD estimator in a simulation study and illustrate its practical use for outlier detection and regression analysis on real-life high-dimensional data sets in chemistry and criminology.
Recommendations
- The feasible solution algorithm for the minimum covariance determinant estimator in multivariate data
- Outlier detection in non-elliptical data by kernel MRCD
- RelaxMCD: smooth optimisation for the minimum covariance determinant estimator
- Asymptotics for the minimum covariance determinant estimator
- Small - sample correction factor of the minimum covariance determinant estimator
Cites work
- A minimal characterization of the covariance matrix
- A well-conditioned estimator for large-dimensional covariance matrices
- Adjustment of an Inverse Matrix Corresponding to a Change in One Element of a Given Matrix
- Alternatives to the Median Absolute Deviation
- An Inverse Matrix Adjustment Arising in Discriminant Analysis
- Asymptotics for the minimum covariance determinant estimator
- Breakdown points of affine equivariant estimators of multivariate location and covariance matrices
- Central limit theorem and influence function for the MCD estimators at general multivariate distributions
- Comments on: ``Robust estimation of multivariate location and scatter in the presence of cellwise and casewise contamination
- Condition-number-regularized covariance estimation
- Exploring multivariate data with the forward search.
- Fast and robust discriminant analysis
- High-breakdown robust multivariate methods
- scientific article; zbMATH DE number 3986407 (Why is no real title available?)
- Influence function and efficiency of the minimum covariance determinant scatter matrix estimator
- Jump robust daily covariance estimation by disentangling variance and correlation components
- Least Median of Squares Regression
- Outlier detection in the multiple cluster setting using the minimum covariance determinant estimator
- Principal component analysis based on robust estimators of the covariance or correlation matrix: influence functions and efficiencies
- Robust estimation of multivariate location and scatter in the presence of cellwise and casewise contamination
- Robust factor analysis.
- Robust Linear Model Selection Based on Least Angle Regression
- Sparse inverse covariance estimation with the graphical lasso
- Tests for standardized generalized variances of multivariate normal populations of possibly different dimensions
- The huge Package for High-dimensional Undirected Graph Estimation in R
- The multivariate least-trimmed squares estimator
Cited in
(48)- Asymptotics for the minimum covariance determinant estimator
- A two-stage Bayesian semiparametric model for novelty detection with robust prior information
- Outlier detection in non-elliptical data by kernel MRCD
- Outlier detection via a block diagonal product estimator
- Testing equality of standardized generalized variances of k multivariate normal populations with arbitrary dimensions
- The power of monitoring: how to make the most of a contaminated multivariate sample
- Outlyingness: which variables contribute most?
- Computing the minimum covariance determinant estimator (MCD) by simulated annealing
- rrcov
- DetMCD in a calibration framework
- Regularized <formula formulatype="inline"><tex Notation="TeX">$M$</tex> </formula>-Estimators of Scatter Matrix
- Small - sample correction factor of the minimum covariance determinant estimator
- Ghost Image Processing for Minimum Covariance Determinants
- Mahalanobis distance based on minimum regularized covariance determinant estimators for high dimensional data
- Modified minimum covariance determinant estimator and its application to outlier detection of chemical process data
- Outlier detection and robust variable selection via the penalized weighted LAD-LASSO method
- The minimum weighted covariance determinant estimator revisited
- Multidimensional outlier detection and robust estimation using S_n covariance
- Minimum regularized covariance determinant and principal component analysis-based method for the identification of high leverage points in high dimensional sparse data
- Consistency factor for the MCD estimator at the Student-\(t\) distribution
- Artificial intelligence in portfolio formation and forecast: Using different variance-covariance matrices
- A robust Hotelling test statistic for one sample case in high dimensional data
- The minimum weighted covariance determinant estimator for high-dimensional data
- Principal component analysis and optimal portfolio
- The minimum covariance determinant estimator for interval-valued data
- Highly robust training of regularized radial basis function networks.
- Outlier detection via a minimum ridge covariance determinant estimator
- Fast Robust Location and Scatter Estimation: A Depth-based Method
- Minimum Regularized Covariance Trace Estimator and Outlier Detection for Functional Data
- The Cellwise Minimum Covariance Determinant Estimator
- Variational inference for semiparametric Bayesian novelty detection in large datasets
- A regularized T-type estimator for high-dimensional data
- On a Stahel-Donoho estimator with skewness-based random projection directions.
- Robust variable selection via the weighted elastic-net multi-step screening procedure
- Dimension reduction for outlier detection in high-dimensional data
- Generalized implementation of invariant coordinate selection with positive semi-definite scatter matrices
- Sparse outlier-robust PCA for multi-source data
- Robust Covariance Estimation and Explainable Outlier Detection for Matrix-Valued Data
- An adaptive threshold for outlier detection in high-dimensional settings
- Efficient computation of sparse and robust maximum association estimators
- Spatially Smoothed Robust Covariance Estimation for Local Outlier Detection
- The R package ecosystem for robust statistics
- CellMCD+: an improved outlier-resistant cellwise minimum covariance determinant method
- The complexity of computing the MCD-estimator
- A Stability Framework for Parameter Selection in the Minimum Covariance Determinant Problem
- Machine learning methods in a random investments problem
- Regularization of robust neural networks: Bayesian connections and outlier detection
- RelaxMCD: smooth optimisation for the minimum covariance determinant estimator
This page was built for publication: The minimum regularized covariance determinant estimator
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q92466)
