Jose Ramon Zubizarreta

Causal inference starts with a simple idea: compare groups that differ by treatment, not much else. Traditionally, similar groups are constructed using only observed covariates; however, it remains a long-standing challenge to incorporate available outcome data into the study design while preserving valid inference. In this paper, we study the general problem of covariate adjustment, effect estimation, and statistical inference when balancing features are constructed or selected with the aid of outcome information from the data. We propose cross-balancing, a method that uses sample splitting to separate the error in feature construction from the error in weight estimation. Our framework addresses two cases: one where the features are learned functions and one where they are selected from a potentially high-dimensional dictionary. In both cases, we establish mild and general conditions under which cross-balancing produces consistent, asymptotically normal, and efficient estimators. In the learned-function case, cross-balancing achieves finite-sample bias reduction relative to plug-in-type estimators, and is multiply robust when the learned features converge at slow rates. In the variable-selection case, cross-balancing only requires a product condition on how well the selected variables approximate true functions. We illustrate cross-balancing in extensive simulations and an observational study, showing that careful use of outcome information can substantially improve both estimation and inference while maintaining interpretability.

Inferring the causal effects of time-varying treatments is often hindered by highly variable inverse propensity weights, particularly in settings with limited covariate overlap. Building on the key framework of Imai and Ratkovic (2015), we establish sufficient balancing conditions for identification in longitudinal studies of treatment effects and propose a novel estimator that directly targets features of counterfactual or potential covariates. Instead of balancing observed covariates, our method balances the components of covariates that are orthogonal to their history, thereby isolating the new information at each time point. This strategy directly targets the joint distribution of potential covariates and prioritizes features that are most relevant to the outcome. We prove that the resulting estimator for the mean potential outcome is consistent and asymptotically normal, even in settings where standard inverse propensity weighting fails. Extensive simulations show that our estimator attains efficiency comparable to that of g-computation while providing superior robustness to model misspecification. We apply our method to a longitudinal study of private versus public schooling in Chile, demonstrating its stability and interpretability in estimating their effects on university admission scores.

Objective: Inverse probability weighting is a fundamental and general methodology for estimating the causal effects of exposures and interventions, but standard approaches to constructing such weights are often suboptimal. Methods: In this paper, we describe a recent approach for constructing such weights that directly balances covariates while optimizing the stability of the resulting weighting estimator. Results: To illustrate the use of this approach in mental health research, we present an exploratory study of the effects of exposure to violence on the risk of suicide attempt. Conclusions: The direct balancing approach to weighting should be given strong consideration in empirical research due to its robustness and transparency in building weighting estimators.

The linear regression model is widely used in the biomedical and social sciences as well as in policy and business research to adjust for covariates and estimate the average effects of treatments. Behind every causal inference endeavor there is a hypothetical randomized experiment. However, in routine regression analyses in observational studies, it is unclear how well the adjustments made by regression approximate key features of randomized experiments, such as covariate balance, study representativeness, sample boundedness, and unweighted sampling. In this paper, we provide software to empirically address this question. We introduce the lmw package for R to compute the implied linear model weights and perform diagnostics for their evaluation. The weights are obtained as part of the design stage of the study; that is, without using outcome information. The implementation is general and applicable, for instance, in settings with instrumental variables and multi-valued treatments; in essence, in any situation where the linear model is the vehicle for adjustment and estimation of average treatment effects with discrete-valued interventions.

Comparison and contrast are the basic means to unveil causation and learn which treatments work. To build good comparison groups, randomized experimentation is key, yet often infeasible. In such non-experimental settings, we illustrate and discuss diagnostics to assess how well the common linear regression approach to causal inference approximates desirable features of randomized experiments, such as covariate balance, study representativeness, interpolated estimation, and unweighted analyses. We also discuss alternative regression modeling, weighting, and matching approaches and argue they should be given strong consideration in empirical work.

The linear regression model is widely used to adjust for covariates and estimate the average effects of treatments. Behind every causal inference endeavor there is a hypothetical randomized experiment. However, in routine regression analyses in observational studies, it is unclear how well the adjustments made by regression approximate key features of randomized experiments, such as covariate balance, study representativeness, sample boundedness, and unweighted sampling. In this paper, we provide software to empirically address this question. We introduce the lmw package for R to compute the implied linear model weights and perform related diagnostics. The weights are obtained as part of the design stage of the study; that is, without using outcome information. The implementation is general and applicable, for instance, in settings with instrumental variables and multi-valued treatments; in essence, in any situation where the linear model is the vehicle for adjustment and estimation of average treatment effects with discrete-valued interventions.

Summary: Weighting is a general and often-used method for statistical adjustment. Weighting has two objectives: first, to balance covariate distributions, and second, to ensure that the weights have minimal dispersion and thus produce a more stable estimator. A recent, increasingly common approach directly optimizes the weights toward these two objectives. However, this approach has not yet been feasible in large-scale datasets when investigators wish to flexibly balance general basis functions in an extended feature space. To address this practical problem, we describe a scalable and flexible approach to weighting that integrates a basis expansion in a reproducing kernel Hilbert space with state-of-the-art convex optimization techniques. Specifically, we use the rank-restricted Nyström method to efficiently compute a kernel basis for balancing in nearly linear time and space, and then use the specialized first-order alternating direction method of multipliers to rapidly find the optimal weights. In an extensive simulation study, we provide new insights into the performance of weighting estimators in large datasets, showing that the proposed approach substantially outperforms others in terms of accuracy and speed. Finally, we use this weighting approach to conduct a national study of the relationship between hospital profit status and heart attack outcomes in a comprehensive dataset of 1.27 million patients. We find that for-profit hospitals use interventional cardiology to treat heart attacks at similar rates as other hospitals but have higher mortality and readmission rates.

Weighting is a general and often-used method for statistical adjustment. Weighting has two objectives: first, to balance covariate distributions, and second, to ensure that the weights have minimal dispersion and thus produce a more stable estimator. A recent, increasingly common approach directly optimizes the weights toward these two objectives. However, this approach has not yet been feasible in large-scale datasets when investigators wish to flexibly balance general basis functions in an extended feature space. For example, many balancing approaches cannot scale to national-level health services research studies. To address this practical problem, we describe a scalable and flexible approach to weighting that integrates a basis expansion in a reproducing kernel Hilbert space with state-of-the-art convex optimization techniques. Specifically, we use the rank-restricted Nyström method to efficiently compute a kernel basis for balancing in {nearly} linear time and space, and then use the specialized first-order alternating direction method of multipliers to rapidly find the optimal weights. In an extensive simulation study, we provide new insights into the performance of weighting estimators in large datasets, showing that the proposed approach substantially outperforms others in terms of accuracy and speed. Finally, we use this weighting approach to conduct a national study of the relationship between hospital profit status and heart attack outcomes in a comprehensive dataset of 1.27 million patients. We find that for-profit hospitals use interventional cardiology to treat heart attacks at similar rates as other hospitals, but have higher mortality and readmission rates.

Federated or multi-site studies have distinct advantages over single-site studies, including increased generalizability, the ability to study underrepresented populations, and the opportunity to study rare exposures and outcomes. However, these studies are challenging due to the need to preserve the privacy of each individual's data and the heterogeneity in their covariate distributions. We propose a novel federated approach to derive valid causal inferences for a target population using multi-site data. We adjust for covariate shift and covariate mismatch between sites by developing multiply-robust and privacy-preserving nuisance function estimation. Our methodology incorporates transfer learning to estimate ensemble weights to combine information from source sites. We show that these learned weights are efficient and optimal under different scenarios. We showcase the finite sample advantages of our approach in terms of efficiency and robustness compared to existing approaches.