Flexible Sensitivity Analysis for Observational Studies Without Observable Implications

In this paper, we provide efficient estimators and honest confidence bands for a variety of treatment effects including local average (LATE) and local quantile treatment effects (LQTE) in data-rich environments. We can handle very many control variables, endogenous receipt of treatment, heterogeneous treatment effects, and function-valued outcomes. Our framework covers the special case of exogenous receipt of treatment, either conditional on controls or unconditionally as in randomized control trials. In the latter case, our approach produces efficient estimators and honest bands for (functional) average treatment effects (ATE) and quantile treatment effects (QTE). To make informative inference possible, we assume that key reduced form predictive relationships are approximately sparse. This assumption allows the use of regularization and selection methods to estimate those relations, and we provide methods for post-regularization and post-selection inference that are uniformly valid (honest) across a wide-range of models. We show that a key ingredient enabling honest inference is the use of orthogonal or doubly robust moment conditions in estimating certain reduced form functional parameters. We illustrate the use of the proposed methods with an application to estimating the effect of 401(k) eligibility and participation on accumulated assets. The results on program evaluation are obtained as a consequence of more general results on honest inference in a general moment condition framework, which arises from structural equation models in econometrics. Here too the crucial ingredient is the use of orthogonal moment conditions, which can be constructed from the initial moment conditions. We provide results on honest inference for (function-valued) parameters within this general framework where any high-quality, modern machine learning methods can be used to learn the nonparametric/high-dimensional components of the model. These include a number of supporting auxilliary results that are of major independent interest: namely, we (1) prove uniform validity of a multiplier bootstrap, (2) offer a uniformly valid functional delta method, and (3) provide results for sparsity-based estimation of regression functions for function-valued outcomes.

Causal inference for non-censored response variables, such as binary or quantitative outcomes, is often based on either (1) direct standardization ('G-formula') or (2) inverse probability of treatment assignment weights ('propensity score'). To do causal inference in survival analysis, one needs to address right-censoring, and often, special techniques are required for that purpose. We will show how censoring can be dealt with 'once and for all' by means of so-called pseudo-observations when doing causal inference in survival analysis. The pseudo-observations can be used as a replacement of the outcomes without censoring when applying 'standard' causal inference methods, such as (1) or (2) earlier. We study this idea for estimating the average causal effect of a binary treatment on the survival probability, the restricted mean lifetime, and the cumulative incidence in a competing risks situation. The methods will be illustrated in a small simulation study and via a study of patients with acute myeloid leukemia who received either myeloablative or non-myeloablative conditioning before allogeneic hematopoetic cell transplantation. We will estimate the average causal effect of the conditioning regime on outcomes such as the 3-year overall survival probability and the 3-year risk of chronic graft-versus-host disease. Copyright © 2017 John Wiley & Sons, Ltd.

This paper provides a review of methodological advancements in the evaluation of heterogeneous treatment effect models based on instrumental variable (IV) methods. We focus on models that achieve identification by assuming monotonicity of the treatment in the IV and analyze local average and quantile treatment effects for the subpopulation of compliers. We start with a comprehensive discussion of the binary treatment and binary IV case as for instance relevant in randomized experiments with imperfect compliance. We then review extensions to identification and estimation with covariates, multi-valued and multiple treatments and instruments, outcome attrition and measurement error, and the identification of direct and indirect treatment effects, among others. We also discuss testable implications and possible relaxations of the IV assumptions, approaches to extrapolate from local to global treatment effects, and the relationship to other IV approaches.

Abstract: Real-world evidence (RWE) studies face bias from confounding, missingness, and informative censoring, limiting credible effect estimation for policy and practice. This study proposes an AI-augmented targeted learning workflow in Stata for average and heterogeneous treatment effects. The approach integrates programmatic cohort construction, principled handling of missing data and censoring, and automated model selection via a Super Learner ensemble that screens candidate learners using cross-validation and meta-learning heuristics. Methods include estimation of nuisance functions for propensity and outcome, targeted maximum likelihood estimation (TMLE) for average treatment effects, and doubly robust DR-learners for conditional effects; robustness checks cover overlap diagnostics, sensitivity to unmeasured confounding, and transportability assessments across sites. In synthetic yet realistic RWE benchmarks, the pipeline attains lower absolute bias and shorter confidence intervals while retaining nominal coverage, with stable runtimes suitable for routine analyses. Implications include an auditable, reproducible pathway to deploy targeted learning within standard Stata workflows, enabling decision-grade RWE under common data irregularities; limitations involve reliance on positivity, data quality, and the external validity of simulated scenarios. This matters because health and policy stakeholders require defensible causal estimates from imperfect observational data. What is provided is an end-to-end template, with diagnostics and reporting artifacts aligned to regulatory expectations. Keywords Real-world evidence, Stata, Targeted maximum likelihood estimation, Super Learner, Doubly robust estimation, Propensity score, Causal inference, Treatment effect heterogeneity, DR-learner, Sensitivity analysis, Positivity and overlap, Reproducible analytics

ABSTRACTBackgroundSurvey data are essential in paediatric epidemiology, providing valuable insights into child health outcomes. The potential outcomes framework has advanced causal inference using observational data. However, traditional design‐based adjustments, especially sample weights, are often overlooked. This omission limits the ability to generalise findings to the broader population.ObjectiveThis study demonstrates three approaches for estimating the population average treatment effect (PATE) in a practical example, examining the impact of household second‐hand smoke (SHS) exposure on blood pressure in school‐aged children.MethodsUsing data from the National Health and Nutrition Examination Survey (NHANES) 2017–2020, we assessed the effect of household SHS exposure, a non‐randomised treatment, on blood pressure in school‐aged children. We applied estimators based on Inverse Probability of Treatment Weighting (IPTW), G‐computation, Targeted Maximum Likelihood Estimation (TMLE), and regression adjustment. Models without adjustments were run for comparison. We examined point estimates and the efficiency of the estimates obtained from these methods.ResultsThe largest differences were observed between the unadjusted regression models and the fully adjusted methods (IPTW, G‐computation, and TMLE), which account for both confounding and survey weights. While the inclusion of the sample weights leads to wider confidence intervals for all methods, G‐computation and TMLE showed comparatively narrower confidence intervals. Confidence intervals for the models not adjusted for sample weights were likely underestimated.ConclusionsThis study highlights the important role of sample weights in causal inference. Generalisability of the average treatment effect as estimated on data sampled using common survey designs to a defined population requires the use of sample weights. The estimators described provide a framework for incorporating sample weights, and their use in health research is recommended.

ObjectivesTo study the effect of Conditional Release (C.R.) on recidivism. To compare this effect along different recidivism risk levels, to evaluate whether risk-assessment-based policies that prioritize people in lower risk categories for release maximally reduce recidivism.MethodsWe use a dataset of 22,726 incarcerated persons released from 87 prison centers in Spain. We apply multiple causal inference methods including Propensity Score Matching (PSM), Inverse Propensity score Weighting (IPW), and Augmented Inverse Propensity Weighting (AIPW) to determine Average Treatment Effect (ATE) of C.R. on recidivism.ResultsGranting C.R. significantly reduces violent and general recidivism risks.ConclusionsThe results suggest that C.R. can promote a safe and supervised return to the community while protecting public safety. ATEs obtained through causal inference methods suggest that granting C.R. exclusively to low-risk inmates does not lead to the maximum reduction of recidivism, and hence we propose alternatives to be studied further.

We partially identify population treatment effects in observational data under sample selection, without the benefit of random treatment assignment. We provide bounds both for the average and the quantile population treatment effects, combining assumptions for the selected and the non-selected subsamples. We show how different assumptions help narrow identification regions, and illustrate our methods by partially identifying the effect of maternal education on the 2015 PISA math test scores in Brazil. We find that while sample selection increases considerably the uncertainty around the effect of maternal education, it is still possible to calculate informative identification regions.

Due to the heterogeneity of low-grade gliomas (LGGs), the lack of randomized control trials, and strong clinical evidence, the effect of the extent of resection (EOR) is currently controversial. To determine the best choice between subtotal resection (STR) and gross-total resection (GTR) for individual patients and to identify features that are potentially relevant to treatment heterogeneity. Patients were enrolled from the SEER database. We used a novel DL approach to make treatment recommendations for patients with LGG. We also made causal inference of the average treatment effect (ATE) of GTR compared with STR. The patients were divided into the Consis. and In-consis. groups based on whether their actual treatment and model recommendations were consistent. Better brain cancer-specific survival (BCSS) outcomes in the Consis. group was observed. Overall, we also identified two subgroups that showed strong heterogeneity in response to GTR. By interpreting the models, we identified numerous variables that may be related to treatment heterogeneity. This is the first study to infer the individual treatment effect, make treatment recommendation, and guide surgical options through deep learning approach in LGG research. Through causal inference, we found that heterogeneous responses to STR and GTR exist in patients with LGG. Visualization of the model yielded several factors that contribute to treatment heterogeneity, which are worthy of further discussion.

ObjectivesTo have confidence in one's interpretation of treatment effects assessed by comparing trial results to external controls, minimizing bias is a critical step. We sought to investigate different methods for causal inference in simulated data sets with measured and unmeasured confounders.MethodsThe simulated data included three types of outcomes (continuous, binary, and time-to-event), treatment assignment, two measured baseline confounders, and one unmeasured confounding factor. Three scenarios were set to create different intensities of confounding effect (e.g., small and blocked confounding paths, medium and blocked confounding paths, and one large unblocked confounding path for scenario 1 to 3, respectively) caused by the unmeasured confounder. The methods of g-computation (GC), inverse probability of treatment weighting (IPTW), overlap weighting (OW), standardized mortality/morbidity ratio (SMR), and targeted maximum likelihood estimation (TMLE) were used to estimate average treatment effects and reduce potential biases.ResultsThe results with the greatest extent of biases were from the raw model that ignored all the potential confounders. In scenario 2, the unmeasured factor indirectly influenced the treatment assignment through a measured controlling factor and led to medium confounding. The methods of GC, IPTW, OW, SMR, and TMLE removed most of bias observed in average treatment effects for all three types of outcomes from the raw model. Similar results were found in scenario 1, but the results tended to be biased in scenario 3. GC had the best performance followed by OW.ConclusionsThe aforesaid methods can be used for causal inference in externally controlled studies when there is no large, unblockable confounding path for an unmeasured confounder. GC and OW are the preferable approaches.

School aversion is increasingly recognized in adolescents and has been linked to emotional distress, suicide risk, and academic failure. However, studies rely on correlational analysis, making it unclear which risk factors truly cause school aversion. To address this gap, we combined directed acyclic graph (DAG)-based modeling, DoWhy-based causal effect estimation, and counterfactual simulation to explore psychosocial pathways related to school aversion in clinically referred adolescents. Participants were clinically referred adolescents from mental health services who completed standardized psychosocial assessments. Variables were obtained through validated instruments and clinical intake records, covering demographics, adversity, personality, and symptoms. Causal inference was conducted through a combined framework of DAG learning, DoWhy estimation with backdoor propensity-score weighting and logistic-model-based counterfactual simulation. All analyses were performed using Python 3.11.8, with pgmpy, DoWhy, and scikit-learn as core libraries. A total of 423 adolescents were assessed, with 57.7% showing school aversion or refusal and 39.7% reporting suicidal thoughts or attempts. DAG modeling identified several school aversion-adjacent relationships, with family structure, bullying, and digital addiction retained as primary school-aversion-centered pathways in downstream analyses, whereas trauma remained a nearby contextual factor. DoWhy analysis showed that the retained associations were SchoolAversion → Bullying [average treatment effect (ATE) = 0.046, p = 0.001] and SchoolAversion → DigitalAdd (ATE = 0.036, p = 0.008), while family structure showed a significant negative effect on school aversion (ATE = -0.162, p = 0.031). Counterfactual simulation showed that removing bullying or digital addiction had relatively small effects on school aversion. In exploratory counterfactual simulations, SchoolAversion → Suicide showed a risk difference of 0.266 (bootstrap95% CI 0.182 to 0.346). Among clinically referred adolescents, school aversion appeared not only as an outcome linked to upstream psychosocial context, but also as a central factor associated with downstream bullying, digital addiction, and suicide risk in the present framework. This integrated causal framework may help refine risk screening and intervention prioritization in clinical populations, while further validation in non-clinical and longitudinal samples is needed.

O estudo busca mensurar o efeito das condições de saúde sobre o rendimento dos trabalhadores brasileiros, usando dados da PNAD de 2008. Para tanto, foram estimados o efeito de tratamento médio e quantílico com correção para o viés de seleção; o método de Lewbel (2012) que gera instrumentos internos a partir da heterocedasticidade dos resíduos e bounds para o efeito do tratamento seguindo Oster (2015). Os resultados mostram um impacto negativo de uma má condição de saúde na renda do trabalho para todas as especificações utilizadas, sendo o maior impacto sofrido por indivíduos localizados nos quantis mais baixos de renda.

When the Data Are Out: Measuring Behavioral Changes Following a Data Breach

In the presence of treatment effect heterogeneity, the average treatment effect (ATE) in a randomized controlled trial (RCT) may differ from the average effect of the same treatment if applied to a target population of interest. If all treatment effect moderators are observed in the RCT and in a dataset representing the target population, then we can obtain an estimate for the target population ATE by adjusting for the difference in the distribution of the moderators between the two samples. This paper considers sensitivity analyses for two situations: (1) where we cannot adjust for a specific moderator $V$ observed in the RCT because we do not observe it in the target population; and (2) where we are concerned that the treatment effect may be moderated by factors not observed even in the RCT, which we represent as a composite moderator $U$. In both situations, the outcome is not observed in the target population. For situation (1), we offer three sensitivity analysis methods based on (i) an outcome model, (ii) full weighting adjustment and (iii) partial weighting combined with an outcome model. For situation (2), we offer two sensitivity analyses based on (iv) a bias formula and (v) partial weighting combined with a bias formula. We apply methods (i) and (iii) to an example where the interest is to generalize from a smoking cessation RCT conducted with participants of alcohol/illicit drug use treatment programs to the target population of people who seek treatment for alcohol/illicit drug use in the US who are also cigarette smokers. In this case a treatment effect moderator is observed in the RCT but not in the target population dataset.

Based on benchmarking various methods and analyzing multiple real scRNA-seq datasets, a computational platform/workflow and a set of tips for best practices are developed for analyzing causal interactions or relationships in single cells.

Unequal cluster sizes are common in cluster randomized trials (CRTs). While there are a number of previous investigations studying the impact of unequal cluster sizes on the power for testing the average treatment effect in CRTs, little is known about the impact of unequal cluster sizes on the power for testing the heterogeneous treatment effect (HTE) in CRTs. In this work, we expand the sample size procedures for studying HTE in CRTs to accommodate cluster size variation under the linear mixed model framework. Through analytical derivation and graphical exploration, we show that the sample size for the HTE with an individual-level effect modifier is less affected by unequal cluster sizes than with a cluster-level effect modifier. The impact of cluster size variability jointly depends on the mean and coefficient of variation of cluster sizes, covariate intraclass correlation coefficient (ICC) and the conditional outcome ICC. In addition, we demonstrate that the HTE-motivated analysis of covariance framework can be used for analyzing the average treatment effect, and offer a more efficient sample size procedure for studying the average treatment effect adjusting for the effect modifier. We use simulations to confirm the accuracy of the proposed sample size procedures for both the average treatment effect and HTE in CRTs. Extensions to multivariate effect modifiers are provided and our procedure is illustrated in the context of the Strategies to Reduce Injuries and Develop Confidence in Elders trial.