Robust feature screening procedures for single and mixed types of data

ABSTRACT Feature screening procedures aim to reducing the dimensionality of data with exponentially-growing dimensions. Existing procedures all focused on a single type of predictors, which are either all continuous or all discrete. They cannot address mixed types of variables, outliers, or nonlinear trends. In this paper we first propose new feature screening procedure(s) for different continuous/discrete combinations of response and predictor variables. They are respectively based on marginal Spearman correlation, marginal ANOVA test, marginal Kruskal-Wallis test, Kolmogorov-Smirnov test, Mann-Whitney test, and smoothing splines modeling. Extensive simulation studies are performed to compare the new and existing procedures, with the aim of identifying a best robust screening procedure for each single type of data. Then we combine these best screening procedures to form the robust feature screening procedure for mixed type of data. We demonstrate its robustness against outliers and model misspecification through simulation studies and a real example.

• Publication year

  2020

• Venue

  Journal of Statistical Computation and Simulation

• Publication date

  2020-02-04

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1080/00949655.2020.1719104
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Prediction and Classification of Cardiac Arrhythmia

  2021cited by this paper
• Variable Selection

  2019cited by this paper
• Generalized Additive Models: An Introduction with R (2nd Edition)

  2018cited by this paper
• Robust model-free feature screening via quantile correlation

  2016cited by this paper
• Discourse of motherhood in Mahasweta Devi's selected works

  2016cited by this paper
• Model-Free Feature Screening for Ultrahigh Dimensional Discriminant Analysis

  2015cited by this paper
• Variable selection in linear models

  2014cited by this paper
• Feature Screening for Ultrahigh Dimensional Categorical Data With Applications

  2014cited by this paper
• Cardiac Arrhythmia Classification Using Neural Networks with Selected Features

  2013cited by this paper
• The Kolmogorov filter for variable screening in high-dimensional binary classification

  2013cited by this paper
• Feature Screening via Distance Correlation Learning

  2012cited by this paper
• Integrating genetic and gene expression evidence into genome-wide association analysis of gene sets.

  2011cited by this paper
• Model-Free Feature Screening for Ultrahigh-Dimensional Data

  2011influential reference
• Integrating pathway analysis and genetics of gene expression for genome-wide association studies.

  2010cited by this paper
• Nearly unbiased variable selection under minimax concave penalty

  2010cited by this paper
• Robust rank correlation based screening

  2010influential reference
• Using Generalized Correlation to Effect Variable Selection in Very High Dimensional Problems

  2009cited by this paper
• Nonparametric Independence Screening in Sparse Ultra-High-Dimensional Additive Models

  2009influential reference
• Ultrahigh Dimensional Feature Selection: Beyond The Linear Model

  2009cited by this paper
• Sure independence screening in generalized linear models with NP-dimensionality

  2009cited by this paper
• Forward Regression for Ultra-High Dimensional Variable Screening

  2009cited by this paper
• GSEA-SNP: applying gene set enrichment analysis to SNP data from genome-wide association studies

  2008cited by this paper
• Extended Bayesian information criteria for model selection with large model spaces

  2008cited by this paper
• Discussion of "Sure independence screening for ultra-high dimensional feature space" by Fan and Lv.

  2008cited by this paper
• Pathway-based approaches for analysis of genomewide association studies.

  2007cited by this paper
• Generalized Additive Models: An Introduction With R

  2007cited by this paper
• High Dimensional Classification Using Features Annealed Independence Rules.

  2007cited by this paper
• Generalized Additive Models

  2006cited by this paper
• Sure independence screening for ultrahigh dimensional feature space

  2006cited by this paper
• The Adaptive Lasso and Its Oracle Properties

  2006cited by this paper
• Editorial - Tutorial on microarray gene expression experiments: An introduction

  2005cited by this paper
• Tutorial on Microarray Gene Expression Experiments

  2005cited by this paper
• PAGE: Parametric Analysis of Gene Set Enrichment

  2005cited by this paper
• Testing Differential Gene Expression in Functional Groups

  2005cited by this paper
• Smoothing spline Gaussian regression: more scalable computation via efficient approximation

  2004influential reference
• A global test for groups of genes: testing association with a clinical outcome

  2004cited by this paper
• Smoothing Spline Anova Models

  2002cited by this paper
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties

  2001cited by this paper
• Some Comments on Cp

  2000cited by this paper
• Risk bounds for model selection via penalization

  1999cited by this paper
• Regression Shrinkage and Selection via the Lasso

  1996cited by this paper
• The risk inflation criterion for multiple regression

  1994cited by this paper
• A Statistical View of Some Chemometrics Regression Tools

  1993cited by this paper
• Estimating the Dimension of a Model

  1978cited by this paper
• Cross‐Validatory Choice and Assessment of Statistical Predictions

  1976cited by this paper
• Some Comments onCp

  1973cited by this paper
• Information Theory and an Extension of the Maximum Likelihood Principle

  1973cited by this paper
• Use of Ranks in One-Criterion Variance Analysis

  1952cited by this paper

• Plasma SOMAmer proteomics of postoperative delirium

  2024cites this paper