Double Machine Learning for Partially Linear Mixed-Effects Models with Repeated Measurements

DOI10.48550/ARXIV.2108.13657arXiv2108.13657OpenAlexW4324056901MaRDI QIDQ115461FDOQ115461

Corinne Emmenegger, Corinne Emmenegger, Peter Bühlmann, Peter Bühlmann

Publication date: 31 August 2021

Published in: Scandinavian Journal of Statistics (Search for Journal in Brave)

Abstract: Traditionally, spline or kernel approaches in combination with parametric estimation are used to infer the linear coefficient (fixed effects) in a partially linear mixed-effects model for repeated measurements. Using machine learning algorithms allows us to incorporate complex interaction structures and high-dimensional variables. We employ double machine learning to cope with the nonparametric part of the partially linear mixed-effects model: the nonlinear variables are regressed out nonparametrically from both the linear variables and the response. This adjustment can be performed with any machine learning algorithm, for instance random forests, which allows to take complex interaction terms and nonsmooth structures into account. The adjusted variables satisfy a linear mixed-effects model, where the linear coefficient can be estimated with standard linear mixed-effects techniques. We prove that the estimated fixed effects coefficient converges at the parametric rate, is asymptotically Gaussian distributed, and semiparametrically efficient. Two simulation studies demonstrate that our method outperforms a penalized regression spline approach in terms of coverage. We also illustrate our proposed approach on a longitudinal dataset with HIV-infected individuals. Software code for our method is available in the R-package dmlalg.

Full work available at URL: https://arxiv.org/abs/2108.13657

zbMATH Keywords

longitudinal datasemiparametric estimationdependent databetween-group heterogeneityCD4 dataset (HIV)double machine learningfixed effects estimation

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Title not available (Why is that?)
• Mixed-Effects Models in S and S-PLUS
• Title not available (Why is that?)
• Statistics for high-dimensional data. Methods, theory and applications.
• Random forests
• Random-Effects Models for Longitudinal Data
• Simultaneous analysis of Lasso and Dantzig selector
• Square-root lasso: pivotal recovery of sparse signals via conic programming
• Double/debiased machine learning for treatment and structural parameters
• Linear mixed models for longitudinal data
• Least squares after model selection in high-dimensional sparse models
• \(\ell_1\)-penalized quantile regression in high-dimensional sparse models
• Sparse models and methods for optimal instruments with an application to eminent domain
• Title not available (Why is that?)
• Mixed Models
• Title not available (Why is that?)
• Analysis of asynchronous longitudinal data with partially linear models
• Robust estimation in partial linear mixed model for longitudinal data
• Penalized quasi-likelihood estimation in partial linear models
• Kernel estimation in semiparametric mixed effect longitudinal modeling
• Robust estimation in generalized semiparametric mixed models for longitudinal data
• Statistical Methods for the Analysis of Repeated Measurements
• Estimation for high-dimensional linear mixed-effects models using \(\ell_1\)-penalization
• Fixed and Random Effects Selection in Mixed Effects Models
• Joint Variable Selection for Fixed and Random Effects in Linear Mixed-Effects Models
• On Variance Components in Semiparametric Mixed Models for Longitudinal Data
• Generalized Linear Mixed Models with Varying Coefficients for Longitudinal Data
• Robustified Maximum Likelihood Estimation in Generalized Partial Linear Mixed Model for Longitudinal Data
• Kernel Regression Estimation Using Repeated Measurements Data
• Semiparametric Stochastic Mixed Models for Longitudinal Data
• Title not available (Why is that?)
• Semiparametric Regression for Clustered Data Using Generalized Estimating Equations
• Doubly robust estimation of partially linear models for longitudinal data with dropouts and measurement error in covariates
• Improved rates and asymptotic normality for nonparametric neural network estimators
• Semiparametric Models for Longitudinal Data with Application to CD4 Cell Numbers in HIV Seroconverters
• Analysis of Testing‐Based Forward Model Selection
• High-dimensional generalized semiparametric model for longitudinal data
• Multivariate t semiparametric mixed-effects model for longitudinal data with multiple characteristics
• Fixed Effects Testing in High-Dimensional Linear Mixed Models
• Joint partially linear model for longitudinal data with informative drop‐outs
• Efficient Semiparametric Marginal Estimation for Longitudinal/Clustered Data
• Inference for High-Dimensional Linear Mixed-Effects Models: A Quasi-Likelihood Approach
• Generalized partially linear mixed-effects models incorporating mismeasured covariates

Cited In (1)

• dmlalg

This page was built for publication: Double Machine Learning for Partially Linear Mixed-Effects Models with Repeated Measurements

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q115461)