Model-based SIR for dimension reduction
From MaRDI portal
Publication:2275652
DOI10.1016/J.CSDA.2011.05.006zbMATH Open1218.62037arXiv1508.02186OpenAlexW2050083787MaRDI QIDQ2275652FDOQ2275652
Publication date: 9 August 2011
Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)
Abstract: A new dimension reduction method based on Gaussian finite mixtures is proposed as an extension to sliced inverse regression (SIR). The model-based SIR (MSIR) approach allows the main limitation of SIR to be overcome, i.e., failure in the presence of regression symmetric relationships, without the need to impose further assumptions. Extensive numerical studies are presented to compare the new method with some of most popular dimension reduction methods, such as SIR, sliced average variance estimation, principal Hessian direction, and directional regression. MSIR appears sufficiently flexible to accommodate various regression functions, and its performance is comparable with or better, particularly as sample size grows, than other available methods. Lastly, MSIR is illustrated with two real data examples about ozone concentration regression, and hand-written digit classification.
Full work available at URL: https://arxiv.org/abs/1508.02186
Recommendations
- Asymptotic distributions for dimension reduction in the SIR-II method
- Response dimension reduction: model-based approach
- Model averaging assisted sufficient dimension reduction
- Statistical modelling via dimension reduction methods
- Estimation of parameters in a structured SIR model
- Dimension reduction in hierarchical linear models
- Sensitivity analysis based dimension reduction of multiscale models
- Dimension reduction and predictor selection in semiparametric models
- A model-free conditional screening approach via sufficient dimension reduction
- scientific article; zbMATH DE number 3885145
Nonparametric regression and quantile regression (62G08) Estimation in multivariate analysis (62H12)
Cites Work
- Applied Linear Regression
- Title not available (Why is that?)
- Model-Based Clustering, Discriminant Analysis, and Density Estimation
- Finite mixture models
- Sliced Inverse Regression for Dimension Reduction
- How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis
- Model-Based Gaussian and Non-Gaussian Clustering
- Theory & Methods: Special Invited Paper: Dimension Reduction and Visualization in Discriminant Analysis (with discussion)
- On Sliced Inverse Regression With High-Dimensional Covariates
- Comment
- On almost linearity of low dimensional projections from high dimensional data
- Model-based cluster and discriminant analysis with the MIXMOD software
- Title not available (Why is that?)
- Bayes Factors
- Contour regression: a general approach to dimension reduction
- On Directional Regression for Dimension Reduction
- Title not available (Why is that?)
- Likelihood-Based Sufficient Dimension Reduction
- Sufficient Dimension Reduction via Inverse Regression
- Dimension reduction for conditional mean in regression
- On Principal Hessian Directions for Data Visualization and Dimension Reduction: Another Application of Stein's Lemma
- Direction estimation in single-index regressions
- On kernel method for sliced average variance estimation
- Matrix Algebra
- Reweighting to Achieve Elliptically Contoured Covariates in Regression
- Estimating the structural dimension of regressions via parametric inverse regression
- Estimation of inverse mean: an orthogonal series approach
Cited In (11)
- Using DAGs to identify the sufficient dimension reduction in the principal fitted components model
- Nonparametric confidence intervals for conditional quantiles with large-dimensional covariates
- Entropy-based sliced inverse regression
- Title not available (Why is that?)
- Tail dimension reduction for extreme quantile estimation
- A robust proposal of estimation for the sufficient dimension reduction problem
- A new sliced inverse regression method for multivariate response
- Sufficient dimension reduction for clustered data via finite mixture modelling
- Modal Principal Component Analysis
- On central matrix based methods in dimension reduction
- Locally penalized single-index model using B-splines and spherical coordinates
Uses Software
This page was built for publication: Model-based SIR for dimension reduction
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2275652)
