litlas
Log inCreate account

Stability Selection

Authors: Nicolai Meinshausen, Peter Bühlmann - Journal of the Royal Statistical Society Series B (Statistical Methodology) 2010 cited by 2,135

Summary Estimation of structure, such as in variable selection, graphical modelling or cluster analysis, is notoriously difficult, especially for high dimensional data. We introduce stability selection. It is based on subsampling in combination with (high dimensional) selection algorithms. As such, the method is extremely general and has a very wide range of applicability. Stability selection provides finite sample control for some error rates of false discoveries and hence a transparent principle to choose a proper amount of regularization for structure estimation. Variable selection and structure estimation improve markedly for a range of selection methods if stability selection is applied. We prove for the randomized lasso that stability selection will be variable selection consistent even if the necessary conditions for consistency of the original lasso method are violated. We demonstrate stability selection for variable selection and Gaussian graphical modelling, using real and simulated data.

Lasso-type recovery ofsparse representations…Lasso-type recovery of sparse representations for high-dimensional dataOn Model SelectionConsistency of LassoOn Model Selection Consistency of LassoHigh dimensional graphsand variable selection…High dimensional graphs and variable selection with the LassoThe Adaptive Lasso andIts Oracle PropertiesThe Adaptive Lasso and Its Oracle PropertiesSure IndependenceScreening for Ultrahigh…Sure Independence Screening for Ultrahigh Dimensional Feature SpaceBolasso: modelconsistent Lasso…Bolasso: model consistent Lasso estimation through the bootstrapThe sparsity and bias ofthe Lasso selection in…The sparsity and bias of the Lasso selection in high-dimensional linear regressionAdaptive Lasso forsparse high-dimensional…Adaptive Lasso for sparse high-dimensional regression modelsp-Values forHigh-Dimensional…p-Values for High-Dimensional RegressionSimultaneous analysis ofLasso and Dantzig…Simultaneous analysis of Lasso and Dantzig selectorUltrahigh DimensionalFeature Selection…Ultrahigh Dimensional Feature Selection: Beyond The Linear ModelHigh-dimensionalcovariance estimation b…High-dimensional covariance estimation by minimizing ℓ1-penalized log-determinant divergenceOverview ofLASSO-related penalized…Overview of LASSO-related penalized regression methods for quantitative trait mapping and genomic selectionMouse obesity networkreconstruction with a…Mouse obesity network reconstruction with a variational Bayes algorithm to employ aggressive false positive controlOn asymptoticallyoptimal confidence…On asymptotically optimal confidence regions and tests for high-dimensional modelsA significance test forthe lassoA significance test for the lassoParameter-FreeHigh-Dimensional…Parameter-Free High-Dimensional Screening Using Multiple Grouping of VariablesA sparse ising modelwith covariatesA sparse ising model with covariatesUsing Lasso forPredictor Selection and…Using Lasso for Predictor Selection and to Assuage Overfitting: A Method Long Overlooked in Behavioral SciencesExtensions of stabilityselection using…Extensions of stability selection using subsamples of observations and covariatesEstimating heterogeneousgraphical models for…Estimating heterogeneous graphical models for discrete data with an application to roll call votingExploration ofPredictors for Korean…Exploration of Predictors for Korean Teacher Job Satisfaction via a Machine Learning Technique, Group MnetThe terminating-randomexperiments selector…The terminating-random experiments selector: Fast high-dimensional variable selection with false discovery rate controlTrimming stabilityselection increases…Trimming stability selection increases variable selection robustnessStability SelectionStability SelectionEarlier referencesFocus paperCiting papersOlderNewer

Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.