Adaptive sparsening and smoothing of the treatment model for longitudinal causal inference using outcome-adaptive LASSO and marginal fused LASSO

2024-10-10

AI Summary

Causal variable selection under time-varying treatments is challenged by dynamic confounding, leading to biased effect estimation and model misspecification. Method: We propose a novel longitudinal causal variable selection framework comprising: (1) Longitudinal Outcome-adaptive LASSO (LOAL), the first method enabling time-adaptive covariate screening via outcome-driven penalty tuning; (2) Marginal Fused LASSO, which imposes temporal smoothness constraints on treatment model parameters to mitigate overfitting while preserving asymptotic unbiasedness; and (3) seamless integration with inverse probability weighting (IPW) and augmented IPW (AIPW) estimators for causal effect estimation. Results: Simulations demonstrate substantial reductions in both estimation variance and model misspecification bias. Applied to the NDIT cohort, our method precisely identifies the causal effect of adolescent alcohol initiation timing on early-adulthood depressive symptoms. This work establishes a theoretically rigorous and empirically robust paradigm for variable selection in time-varying causal inference.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Causal variable selection in time-varying treatment settings is challenging due to evolving confounding effects. Existing methods mainly focus on time-fixed exposures and are not directly applicable to time-varying scenarios. We propose a novel two-step procedure for variable selection when modeling the treatment probability at each time point. We first introduce a novel approach to longitudinal confounder selection using a Longitudinal Outcome Adaptive LASSO (LOAL) that will data-adaptively select covariates with theoretical justification of variance reduction of the estimator of the causal effect. We then propose an Adaptive Fused LASSO that can collapse treatment model parameters over time points with the goal of simplifying the models in order to improve the efficiency of the estimator while minimizing model misspecification bias compared with naive pooled logistic regression models. Our simulation studies highlight the need for and usefulness of the proposed approach in practice. We implemented our method on data from the Nicotine Dependence in Teens study to estimate the effect of the timing of alcohol initiation during adolescence on depressive symptoms in early adulthood.

Problem

• Selecting causal variables for time-varying treatments with evolving confounders
• Improving estimator efficiency while minimizing model misspecification bias
• Adapting longitudinal outcome-adaptive LASSO for confounder selection

Innovation

• Longitudinal Outcome Adaptive LASSO confounder selection
• Adaptive Fused LASSO collapses parameters over time
• Two-step procedure improves efficiency reduces bias