Missing values: sparse inverse covariance estimation and an extension to sparse regression

DOI10.1007/S11222-010-9219-7zbMATH Open1322.62115arXiv0903.5463OpenAlexW2077870633MaRDI QIDQ80804FDOQ80804

Nicolas Städler, Peter Bühlmann, Nicolas Städler

Publication date: 3 December 2010

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: We propose an l1-regularized likelihood method for estimating the inverse covariance matrix in the high-dimensional multivariate normal model in presence of missing data. Our method is based on the assumption that the data are missing at random (MAR) which entails also the completely missing at random case. The implementation of the method is non-trivial as the observed negative log-likelihood generally is a complicated and non-convex function. We propose an efficient EM algorithm for optimization with provable numerical convergence properties. Furthermore, we extend the methodology to handle missing values in a sparse regression context. We demonstrate both methods on simulated and real data.

Full work available at URL: https://arxiv.org/abs/0903.5463

zbMATH Keywords

LassoEM algorithmGaussian graphical modelmissing datatwo-stage likelihood

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Estimation in multivariate analysis (62H12) Ridge regression; shrinkage estimators (Lasso) (62J07) Graphical methods in statistics (62A09) Parametric inference under constraints (62F30)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Covariance-regularized regression and classification for high dimensional problems
• Pathwise coordinate optimization
• Convergence of a block coordinate descent method for nondifferentiable minimization
• On the convergence properties of the EM algorithm
• High-dimensional graphs and variable selection with the Lasso
• Sparse inverse covariance estimation with the graphical lasso
• Sparse permutation invariant covariance estimation
• Model selection and estimation in the Gaussian graphical model
• Model Selection Criteria for Missing-Data Problems Using the EM Algorithm
• \(\ell_{1}\)-penalization for mixture regression models
• A note on the Lasso for Gaussian graphical model selection

Cited In (18)

• Learning causal structure from mixed data with missing values using Gaussian copula models
• Variable selection for high‐dimensional generalized linear model with block‐missing data
• Title not available (Why is that?)
• Sparse precision matrix estimation with missing observations
• Concentration of measure bounds for matrix-variate data with missing values
• Calibrated zero-norm regularized LS estimator for high-dimensional error-in-variables regression
• Sparse multivariate regression with missing values and its application to the prediction of material properties
• Estimating high-dimensional covariance and precision matrices under general missing dependence
• Change-Point Detection for Graphical Models in the Presence of Missing Values
• Extending graphical models for applications: on covariates, missingness and normality
• The conditional censored graphical Lasso estimator
• Graphical Model Inference with Erosely Measured Data
• L ₀ -regularization for high-dimensional regression with corrupted data
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• Scalable interpretable learning for multi-response error-in-variables regression
• An ensemble learning method for variable selection: application to high-dimensional data and missing values
• cglasso
• Minimax optimal estimation of high-dimensional sparse covariance matrices with missing data

Uses Software

• glasso
• glmnet
• scout
• impute

This page was built for publication: Missing values: sparse inverse covariance estimation and an extension to sparse regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q80804)