Robust learning for optimal treatment decision with NP-dimensionality

DOI10.1214/16-EJS1178zbMATH Open1419.62445arXiv1510.04378WikidataQ38637969 ScholiaQ38637969MaRDI QIDQ330449FDOQ330449

Authors: Chengchun Shi, Rui Song, Wenbin Lu 

Publication date: 26 October 2016

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

Abstract: In order to identify important variables that are involved in making optimal treatment decision, Lu et al. (2013) proposed a penalized least squared regression framework for a fixed number of predictors, which is robust against the misspecification of the conditional mean model. Two problems arise: (i) in a world of explosively big data, effective methods are needed to handle ultra-high dimensional data set, for example, with the dimension of predictors is of the non-polynomial (NP) order of the sample size; (ii) both the propensity score and conditional mean models need to be estimated from data under NP dimensionality. In this paper, we propose a two-step estimation procedure for deriving the optimal treatment regime under NP dimensionality. In both steps, penalized regressions are employed with the non-concave penalty function, where the conditional mean model of the response given predictors may be misspecified. The asymptotic properties, such as weak oracle properties, selection consistency and oracle distributions, of the proposed estimators are investigated. In addition, we study the limiting distribution of the estimated value function for the obtained optimal treatment regime. The empirical performance of the proposed estimation method is evaluated by simulations and an application to a depression dataset from the STAR*D study.

Full work available at URL: https://arxiv.org/abs/1510.04378

Recommendations

• High-dimensional \(A\)-learning for optimal dynamic treatment regimes
• Quantile-optimal treatment regimes
• Optimal Dynamic Treatment Regimes
• Model-Assisted Uniformly Honest Inference for Optimal Treatment Regimes in High Dimension
• A robust method for estimating optimal treatment regimes

zbMATH Keywords

variable selectionoracle propertynonconcave penalized likelihoodoptimal treatment strategy

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Nonparametric robustness (62G35) Applications of statistics to biology and medical sciences; meta analysis (62P10) Ridge regression; shrinkage estimators (Lasso) (62J07)

Cited In (15)

• High-dimensional \(A\)-learning for optimal dynamic treatment regimes
• High-dimensional inference for personalized treatment decision
• Statistical Learning for Individualized Asset Allocation
• A constrained single‐index regression for estimating interactions between a treatment and covariates
• Relative contrast estimation and inference for treatment recommendation
• Sparse concordance-assisted learning for optimal treatment decision
• Multi-threshold proportional hazards model and subgroup identification
• Functional additive models for optimizing individualized treatment rules
• A high-dimensional single-index regression for interactions between treatment and covariates
• Augmented direct learning for conditional average treatment effect estimation with double robustness
• Model-Assisted Uniformly Honest Inference for Optimal Treatment Regimes in High Dimension
• A single-index model with multiple-links
• Deep advantage learning for optimal dynamic treatment regime
• Multithreshold change plane model: estimation theory and applications in subgroup identification
• Generalization error bounds of dynamic treatment regimes in penalized regression-based learning

This page was built for publication: Robust learning for optimal treatment decision with NP-dimensionality

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q330449)