High Dimensional Variable Selection via Tilting
From MaRDI portal
Abstract: The paper considers variable selection in linear regression models where the number of covariates is possibly much larger than the number of observations. High dimensionality of the data brings in many complications, such as (possibly spurious) high correlations between the variables, which result in marginal correlation being unreliable as a measure of association between the variables and the response. We propose a new way of measuring the contribution of each variable to the response which takes into account high correlations between the variables in a data-driven way. The proposed tilting procedure provides an adaptive choice between the use of marginal correlation and tilted correlation for each variable, where the choice is made depending on the values of the hard thresholded sample correlation of the design matrix. We study the conditions under which this measure can successfully discriminate between the relevant and the irrelevant variables and thus be used as a tool for variable selection. Finally, an iterative variable screening algorithm is constructed to exploit the theoretical properties of tilted correlation, and its good practical performance is demonstrated in a comparative simulation study.
Recommendations
- High-dimensional variable selection
- Variable selection in high dimensional data analysis with applications
- Variable selection in high-dimensional partially linear models
- Variable selection for high dimensional multivariate outcomes
- Variable selection and estimation in high-dimensional partially linear models
- Variable selection in multivariate linear models with high-dimensional covariance matrix estimation
- A Selective Overview of Variable Selection in High Dimensional Feature Space (Invited Review Article)
- Variable selection in high-dimension with random designs and orthogonal matching pursuit
- High-dimensional variable selection with reciprocal \(L_{1}\)-regularization
- Variable selection via combined penalization for high-dimensional data analysis
Cited in
(35)- Feature Screening for Massive Data Analysis by Subsampling
- Goodness-of-fit testing-based selection for large-p-small-n problems: a two-stage ranking approach
- Exploring dependence between categorical variables: benefits and limitations of using variable selection within Bayesian clustering in relation to log-linear modelling with interaction terms
- Ranking-based variable selection for high-dimensional data
- Covariance-insured screening
- Group sparse recovery via group square-root elastic net and the iterative multivariate thresholding-based algorithm
- Variable selection via partial correlation
- Dynamic tilted current correlation for high dimensional variable screening
- Ranking based variable selection for censored data using AFT models
- A note on marginal correlation based screening
- Jackknife model averaging for expectile regressions in increasing dimension
- Testing a single regression coefficient in high dimensional linear models
- Principal minimax support vector machine for sufficient dimension reduction with contaminated data
- Adaptive conditional feature screening
- Threshold Estimation via Group Orthogonal Greedy Algorithm
- Modified martingale difference correlations
- Variable selection for survival data with a class of adaptive elastic net techniques
- Jackknife model averaging for quantile single-index coefficient model
- Jackknife model averaging for additive expectile prediction
- Cluster feature selection in high-dimensional linear models
- A selective overview of feature screening methods with applications to neuroimaging data
- Which bridge estimator is the best for variable selection?
- Jackknife model averaging for mixed-data kernel-weighted spline quantile regressions
- Ultrahigh dimensional feature screening via projection
- High-dimensional variable selection via low-dimensional adaptive learning
- Robust variable selection via the weighted elastic-net multi-step screening procedure
- F-test and z-test for high-dimensional regression models with a factor structure
- Prior Knowledge Guided Ultra-High Dimensional Variable Screening With Application to Neuroimaging Data
- Semi-Standard Partial Covariance Variable Selection When Irrepresentable Conditions Fail
- Enmsp: an elastic-net multi-step screening procedure for high-dimensional regression
- Selection by partitioning the solution paths
- Fast feature selection via streamwise procedure for massive data
- High-dimensional variable selection
- High-dimensional variable screening under multicollinearity
- Ultra-high dimensional variable screening via Gram-Schmidt orthogonalization
This page was built for publication: High Dimensional Variable Selection via Tilting
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4632676)
