instrument construction

Causal structure learning under unobserved confounding and potentially invalid instrumental variables (IVs) remains challenging. Method: We propose a semiparametric proxy IV approach that constructs valid proxy IVs to achieve identifiability of causal graphs in nonlinear, semiparametric settings—even when some IVs are partially invalid. The method integrates semiparametric structural equation modeling, kernel smoothing estimation, and adaptive-threshold graph inference. Contribution/Results: We establish theoretical guarantees: consistent causal graph recovery, asymptotically normal causal effect estimation, and false discovery rate (FDR) control in edge identification. Extensive simulations demonstrate substantial performance gains over state-of-the-art methods. Applied to Alzheimer’s disease gene regulatory network inference, our approach successfully identifies key pathogenic pathways, validating its practical utility and biological interpretability.

This paper addresses the challenge of identifying causal effects in the presence of unobserved confounding. We propose a nonparametric causal inference framework applicable to both multi-valued and continuous instrumental variables (IVs). Building upon the additive IV model, our approach identifies average potential outcomes and average treatment effects via a weighting function. Leveraging semiparametric efficiency theory, we derive the efficient influence function and construct a debiased machine learning estimator that achieves asymptotically normal and consistent estimation of causal effects. The method naturally extends to longitudinal data and dynamic treatment regimes. In simulations and an empirical application using the Job Training Partnership Act (JTPA) dataset, it substantially reduces finite-sample bias and improves statistical inference accuracy. To our knowledge, this is the first unified framework that establishes nonparametric identification and robust estimation for general IVs—covering both discrete and continuous instruments—under unobserved confounding.

This study addresses the estimation bias arising from endogeneity in regression models by proposing a general and computationally efficient semiparametric projection method. The approach constructs endogenous instrumental variables by projecting and expanding the conditional mean function of the structural error onto the space of explanatory variables, thereby avoiding reliance on conventional exogenous instruments or specific parametric model forms. It is applicable to linear, nonlinear, and semiparametric settings alike. By integrating LASSO-based variable selection with asymptotic theory, the paper establishes identification conditions and asymptotic properties of the resulting estimator. Extensive simulations and empirical analyses demonstrate the method’s strong finite-sample performance, confirming its practical utility in mitigating endogeneity bias across diverse modeling contexts.

Identifying and validating valid instrumental variables (IVs) remains a major bottleneck in causal inference due to the difficulty of establishing exogeneity, relevance, and exclusion restrictions. Method: This study introduces the first large language model (LLM)-based framework for automated IV search and validity justification. It employs a novel multi-step role-playing prompting strategy that enables the LLM to emulate economists’ endogenous modeling and counterfactual reasoning, integrating domain knowledge to generate interpretable, narrative-style validity arguments. The framework uniquely extends AI-assisted IV discovery to three canonical quasi-experimental designs: control variable selection, difference-in-differences (DID), and regression discontinuity design (RDD). Contribution/Results: Evaluated across three classic empirical domains—returns to education, supply-demand analysis, and peer effects—the framework successfully identifies and validates multiple novel IVs, substantially improving search efficiency and argument rigor. It establishes a reproducible, methodology-driven paradigm for AI-augmented empirical economics.

Estimating causal effects from observational data requires selecting appropriate control and instrumental variables that satisfy causal identification conditions—a challenging task often reliant on strong domain knowledge or ad hoc assumptions. Method: This paper proposes the first end-to-end joint learning framework that automatically identifies valid combinations of control and instrumental variables. Grounded in conditional independence testing, the method integrates nonparametric dependence measures with structural search optimization, ensuring statistical consistency in variable selection under mild regularity conditions. Contribution/Results: Unlike conventional approaches requiring prespecified variable sets or strong prior assumptions, our framework is fully data-driven. In simulations, it achieves significantly higher variable identification accuracy. Empirically, applied to the Job Corps study, its estimated treatment effect closely aligns with results from the randomized controlled trial—demonstrating both validity and robustness in real-world causal inference.

This study addresses the challenge of efficiently estimating causal effects under confounding when experimental budgets are limited. The authors propose a novel approach that integrates instrumental variable regression with Gaussian graphical models, leveraging prior knowledge of partial joint distributions to optimize the allocation between fully observed samples and partially observed data (e.g., only \(X_{12}\)). Under a fixed budget constraint, this method analytically derives the optimal sampling scheme that minimizes the asymptotic variance of the causal effect estimator—a solution not previously available in closed form. Theoretical analysis demonstrates that the proposed allocation significantly reduces both the total budget and the number of complete observations required to detect non-zero causal effects. Empirical validation in automotive analytics and drug discovery underscores the method’s practical utility alongside its theoretical contributions.

This study addresses the limitation of conventional instrumental variable (IV) methods, which often assume a constant treatment effect and thus struggle to accommodate effect heterogeneity in real-world settings. Building on the local average treatment effect (LATE) framework, the paper systematically integrates covariate-adjusted IV approaches, clarifying how covariates influence the weighting structure of LATE estimators. It proposes flexible modeling strategies to avoid parametric misspecification and incorporates robust diagnostic tests for violations of the monotonicity assumption. By combining nonparametric and semiparametric estimation techniques, formal hypothesis testing, and accompanying software implementation, this work offers empirical researchers a theoretically rigorous yet practically feasible causal inference workflow, substantially enhancing the reliability and applicability of IV analysis.

This study addresses the construction of valid granular instrumental variables (GIVs) in factor models subject to potential aggregate shocks. By characterizing the orthogonal complement of the factor loading space, it establishes a novel link between GIV validity and this orthogonal structure, yielding a feasible estimation procedure that neither requires knowledge of the factor loadings nor relies on a large cross-sectional dimension. The proposed method is accompanied by formal inference and specification testing procedures. By circumventing the conventional dependence on high-dimensional cross-sectional data, the approach substantially enhances the flexibility and applicability of instrumental variable methods. An empirical application to estimating stock market multipliers reveals pronounced heterogeneity in equity demand elasticities across investor sectors, providing refined evidence supporting the inelastic markets hypothesis.

This study addresses the challenge of conducting instrumental variable analysis when the exclusion restriction and exogeneity assumptions are difficult to verify and the standard first-stage monotonicity condition fails to hold. The authors propose a novel nonparametric sensitivity analysis framework that relaxes these conventional assumptions, enabling identification of sharp bounds on the marginal distributions of potential outcomes and their functionals—such as the average treatment effect—without imposing monotonicity or restricting treatment effect heterogeneity. The resulting identification problem is cast as a linear program with favorable theoretical properties, accompanied by a computationally feasible estimation strategy suitable for infinite-dimensional settings. Empirically, the method is applied to estimate peer effects in movie attendance using weather as an imperfect instrument, demonstrating its practical utility and robustness.

Traditional instrumental variable methods rely on the stringent assumption that the structural equation model holds exactly—a condition often violated in practice, leading to invalid inference. This work proposes a novel inference framework based on debiased least squares and inverse problem regularization, which defines a target parameter that coincides with conventional estimands when the structural model is correctly specified yet remains well-defined and inferable even under model misspecification. By relaxing the requirement of exact structural equation validity, the approach ensures robust statistical inference under substantially weaker conditions, thereby significantly enhancing the reliability and applicability of instrumental variable methods in realistic settings.