Causal Decomposition Analysis with Synergistic Interventions: A Triply-Robust Machine Learning Approach to Addressing Multiple Dimensions of Social Disparities

2025-06-23

AI Summary

Educational disparities stem from the intersection of racial, socioeconomic, and geographic inequalities; thus, unidimensional interventions yield limited efficacy for multiply marginalized populations. This paper proposes a causal decomposition framework for multidimensional synergistic interventions—the first to extend causal decomposition to joint, cross-domain interventions targeting racial gaps in mathematics achievement. Methodologically, we introduce a triply robust estimator that integrates machine learning to model complex relationships among ordered interventions (e.g., high-quality school enrollment plus equitable Algebra I access), mediators, and confounders, thereby mitigating model misspecification bias. Empirical analysis using longitudinal data from U.S. high school students demonstrates that concurrently implementing both interventions significantly narrows mathematics achievement gaps between Black, Hispanic, and White students. Our work advances causal methodology for evaluating multidimensional educational equity interventions, offering a rigorous, scalable approach to quantifying synergistic policy effects.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Educational disparities are rooted in and perpetuate social inequalities across multiple dimensions such as race, socioeconomic status, and geography. To reduce disparities, most intervention strategies focus on a single domain and frequently evaluate their effectiveness by using causal decomposition analysis. However, a growing body of research suggests that single-domain interventions may be insufficient for individuals marginalized on multiple fronts. While interventions across multiple domains are increasingly proposed, there is limited guidance on appropriate methods for evaluating their effectiveness. To address this gap, we develop an extended causal decomposition analysis that simultaneously targets multiple causally ordered intervening factors, allowing for the assessment of their synergistic effects. These scenarios often involve challenges related to model misspecification due to complex interactions among group categories, intervening factors, and their confounders with the outcome. To mitigate these challenges, we introduce a triply robust estimator that leverages machine learning techniques to address potential model misspecification. We apply our method to a cohort of students from the High School Longitudinal Study, focusing on math achievement disparities between Black, Hispanic, and White high schoolers. Specifically, we examine how two sequential interventions - equalizing the proportion of students who attend high-performing schools and equalizing enrollment in Algebra I by 9th grade across racial groups - may reduce these disparities.

Problem

• Addressing multi-dimensional social disparities in education
• Evaluating synergistic effects of multiple-domain interventions
• Mitigating model misspecification in causal decomposition analysis

Innovation

• Extended causal decomposition for multiple interventions
• Triply robust estimator with machine learning
• Assesses synergistic effects of ordered factors