An official website of the United States government
Methicillin-resistant Staphylococcus aureus (MRSA) is a type of bacteria resistant to certain antibiotics, making it difficult to prevent MRSA infections. Among decades of efforts to conquer infectious diseases caused by MRSA, many studies have been proposed to estimate the causal effects of close contact (treatment) on MRSA infection (outcome) from observational data. In this problem, the treatment assignment mechanism plays a key role as it determines the patterns of missing counterfactuals --- the fundamental challenge of causal effect estimation. Most existing observational studies for causal effect learning assume that the treatment is assigned individually for each unit. However, on many occasions, the treatments are pairwisely assigned for units that are connected in graphs, i.e., the treatments of different units are entangled. Neglecting the entangled treatments can impede the causal effect estimation. In this paper, we study the problem of causal effect estimation with treatment entangled in a graph. Despite a few explorations for entangled treatments, this problem still remains challenging due to the following challenges: (1) the entanglement brings difficulties in modeling and leveraging the unknown treatment assignment mechanism; (2) there may exist hidden confounders which lead to confounding biases in causal effect estimation; (3) the observational data is often time-varying. To tackle these challenges, we propose a novel method NEAT, which explicitly leverages the graph structure to model the treatment assignment mechanism, and mitigates confounding biases based on the treatment assignment modeling. We also extend our method into a dynamic setting to handle time-varying observational data. Experiments on both synthetic datasets and a real-world MRSA dataset validate the effectiveness of the proposed method, and provide insights for future applications.
more »
« less
This content will become publicly available on January 1, 2026
Estimating causal effects under non-individualistic treatments due to network entanglement
Summary In many observational studies, the treatment assignment mechanism is not individualistic, as it allows the probability of treatment of a unit to depend on quantities beyond the unit’s covariates. In such settings, unit treatments may be entangled in complex ways. In this article, we consider a particular instance of this problem where the treatments are entangled by a social network among units. For instance, when studying the effects of peer interaction on a social media platform, the treatment on a unit depends on the change of the interactions network over time. A similar situation is encountered in many economic studies, such as those examining the effects of bilateral trade partnerships on countries’ economic growth. The challenge in these settings is that individual treatments depend on a global network that may change in a way that is endogenous and cannot be manipulated experimentally. In this paper, we show that classical propensity score methods that ignore entanglement may lead to large bias and wrong inference of causal effects. We then propose a solution that involves calculating propensity scores by marginalizing over the network change. Under an appropriate ignorability assumption, this leads to unbiased estimates of the treatment effect of interest. We also develop a randomization-based inference procedure that takes entanglement into account. Under general conditions on network change, this procedure can deliver valid inference without explicitly modelling the network. We establish theoretical results for the proposed methods and illustrate their behaviour via simulation studies based on real-world network data. We also revisit a large-scale observational dataset on contagion of online user behaviour, showing that ignoring entanglement may inflate estimates of peer influence.
more »
« less
- Award ID(s):
- 2046880
- PAR ID:
- 10593290
- Publisher / Repository:
- Oxford University Press
- Date Published:
- Journal Name:
- Biometrika
- Volume:
- 112
- Issue:
- 1
- ISSN:
- 1464-3510
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract It is common to conduct causal inference in matched observational studies by proceeding as though treatment assignments within matched sets are assigned uniformly at random and using this distribution as the basis for inference. This approach ignores observed discrepancies in matched sets that may be consequential for the distribution of treatment, which are succinctly captured by within-set differences in the propensity score. We address this problem via covariate-adaptive randomization inference, which modifies the permutation probabilities to vary with estimated propensity score discrepancies and avoids requirements to exclude matched pairs or model an outcome variable. We show that the test achieves type I error control arbitrarily close to the nominal level when large samples are available for propensity score estimation. We characterize the large-sample behaviour of the new randomization test for a difference-in-means estimator of a constant additive effect. We also show that existing methods of sensitivity analysis generalize effectively to covariate-adaptive randomization inference. Finally, we evaluate the empirical value of combining matching and covariate-adaptive randomization procedures using simulations and analyses of genetic damage among welders and right-heart catheterization in surgical patients.more » « less
-
Abstract Propensity score weighting is a tool for causal inference to adjust for measured confounders in observational studies. In practice, data often present complex structures, such as clustering, which make propensity score modeling and estimation challenging. In addition, for clustered data, there may be unmeasured cluster-level covariates that are related to both the treatment assignment and outcome. When such unmeasured cluster-specific confounders exist and are omitted in the propensity score model, the subsequent propensity score adjustment may be biased. In this article, we propose a calibration technique for propensity score estimation under the latent ignorable treatment assignment mechanism, i. e., the treatment-outcome relationship is unconfounded given the observed covariates and the latent cluster-specific confounders. We impose novel balance constraints which imply exact balance of the observed confounders and the unobserved cluster-level confounders between the treatment groups. We show that the proposed calibrated propensity score weighting estimator is doubly robust in that it is consistent for the average treatment effect if either the propensity score model is correctly specified or the outcome follows a linear mixed effects model. Moreover, the proposed weighting method can be combined with sampling weights for an integrated solution to handle confounding and sampling designs for causal inference with clustered survey data. In simulation studies, we show that the proposed estimator is superior to other competitors. We estimate the effect of School Body Mass Index Screening on prevalence of overweight and obesity for elementary schools in Pennsylvania.more » « less
-
We study regressions with multiple treatments and a set of controls that is flexible enough to purge omitted variable bias. We show these regressions generally fail to estimate convex averages of heterogeneous treatment effects—instead, estimates of each treatment’s effect are contaminated by nonconvex averages of the effects of other treatments. We discuss three estimation approaches that avoid such contamination bias, including the targeting of easiest-to-estimate weighted average effects. A reanalysis of nine empirical applications finds economically and statistically meaningful contamination bias in observational studies; contamination bias in experimental studies is more limited due to smaller variability in propensity scores.more » « less
-
Individuals may respond to treatments with significant heterogeneity. To optimize the treatment effect, it is necessary to recommend treatments based on individual characteristics. Existing methods in the literature for learning individualized treatment regimes are usually designed for randomized studies with binary treatments. In this study, we propose an algorithm to extend random forest of interaction trees (Su et al., 2009) to accommodate multiple treatments. By integrating the generalized propensity score into the interaction tree growing process, the proposed method can handle both randomized and observational study data with multiple treatments. The performance of the proposed method, relative to existing approaches in the literature, is evaluated through simulation studies. The proposed method is applied to an assessment of multiple voluntary educational programmes at a large public university.more » « less
