Sparse dimension reduction based on energy and ball statistics
From MaRDI portal
Publication:6161663
DOI10.1007/S11634-021-00470-7arXiv2012.06893MaRDI QIDQ6161663FDOQ6161663
Tim Verdonck, Sven Serneels, Emmanuel Jordy Menvouta
Publication date: 27 June 2023
Published in: Advances in Data Analysis and Classification. ADAC (Search for Journal in Brave)
Abstract: As its name suggests, sufficient dimension reduction (SDR) targets to estimate a subspace from data that contains all information sufficient to explain a dependent variable. Ample approaches exist to SDR, some of the most recent of which rely on minimal to no model assumptions. These are defined according to an optimization criterion that maximizes a nonparametric measure of association. The original estimators are nonsparse, which means that all variables contribute to the model. However, in many practical applications, an SDR technique may be called for that is sparse and as such, intrinsically performs sufficient variable selection (SVS). This paper examines how such a sparse SDR estimator can be constructed. Three variants are investigated, depending on different measures of association: distance covariance, martingale difference divergence and ball covariance. A simulation study shows that each of these estimators can achieve correct variable selection in highly nonlinear contexts, yet are sensitive to outliers and computationally intensive. The study sheds light on the subtle differences between the methods. Two examples illustrate how these new estimators can be applied in practice, with a slight preference for the option based on martingale difference divergence in the bioinformatics example.
Full work available at URL: https://arxiv.org/abs/2012.06893
SDR(sufficient) dimension reduction(sufficient) variable selectionnonparametric multivariate statisticssparse estimatorsSVS
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming
- Partial martingale difference correlation
- Ball Covariance: A Generic Measure of Dependence in Banach Space
- Measuring and testing dependence by correlation of distances
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
- Testing predictor contributions in sufficient dimension reduction.
- Distance covariance in metric spaces
- Sure Independence Screening for Ultrahigh Dimensional Feature Space
- Sliced Inverse Regression with Regularizations
- Hedonic housing prices and the demand for clean air
- The distance correlation \(t\)-test of independence in high dimension
- The Geometry of Algorithms with Orthogonality Constraints
- Shrinkage Inverse Regression Estimation for Model-Free Variable Selection
- Projection pursuit
- Energy statistics: a class of statistics based on distances
- Sparse Sliced Inverse Regression Via Lasso
- Martingale Difference Correlation and Its Use in High-Dimensional Variable Screening
- Sparse sufficient dimension reduction
- Sparse principal component regression via singular value decomposition approach
- Sparse Partial Least Squares Regression for Simultaneous Dimension Reduction and Variable Selection
- Use of Ranks in One-Criterion Variance Analysis
- Dimension reduction based on constrained canonical correlation and variable filtering
- Coordinate-independent sparse sufficient dimension reduction and variable selection
- Principal angles between subspaces in an A-based scalar product: Algorithms and perturbation estimates
- Sequential Sufficient Dimension Reduction for Large p, Small n Problems
- A martingale-difference-divergence-based estimation of central mean subspace
- Robust sufficient dimension reduction via ball covariance
Cited In (1)
This page was built for publication: Sparse dimension reduction based on energy and ball statistics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6161663)
