arXiv subjects

Stijn Vansteelandt

Publications and source records attributed to Stijn Vansteelandt.

At least 19 recordsLinked to original sources

arXiv2026

Targeted learning of heterogeneous treatment effect curves for right censored or left truncated time-to-event data

In recent years, there has been growing interest in causal machine learning estimators for quantifying subject-specific effects of a binary treatment on time-to-event outcomes. Estimation approaches have been proposed which attenuate the inherent regularisation bias in machine learning predictions, with each of these estimators addressing measured confounding, right censoring, and in some cases, left truncation. However, the existing approaches are found to exhibit suboptimal finite-sample performance, with none of the existing estimators fully leveraging the temporal structure of the data, yielding non-smooth treatment effects over time. We address these limitations by introducing surv-iTMLE, a targeted learning procedure for estimating the difference in the conditional survival probabilities under two treatments. Unlike existing estimators, surv-iTMLE accommodates both left truncation and right censoring while enforcing smoothness and boundedness of the estimated treatment effect curve over time. Through extensive simulation studies under both right censoring and left truncation scenarios, we demonstrate that surv-iTMLE outperforms existing methods in terms of bias and smoothness of time-varying effect estimates in finite samples. We then illustrate surv-iTMLE's practical utility by exploring heterogeneity in the effects of immunotherapy on survival among non-small cell lung cancer (NSCLC) patients, revealing clinically meaningful temporal patterns that existing estimators may obscure.

stat.ME↗

arXiv2026

On estimands in target trial emulation

The target trial framework enables causal inference from longitudinal observational data by emulating randomized trials initiated at multiple time points. Precision is often improved by pooling information across trials, with standard models typically assuming - among other things - a time-constant treatment effect. However, this obscures interpretation when the true treatment effect varies, which we argue to be likely as a result of relying on noncollapsible estimands. To address these challenges, this paper introduces a model-free strategy for target trial analysis, centered around the choice of the estimand, rather than model specification. This ensures that treatment effects remain clearly interpretable for well-defined populations even under model misspecification. We propose estimands suitable for different study designs, and develop accompanying G-computation and inverse probability weighted estimators. Applications on simulations and real data on antimicrobial de-escalation in an intensive care unit setting demonstrate the greater clarity and reliability of the proposed methodology over traditional techniques.

stat.ME↗

arXiv2025

Robust evaluation of treatment effects in longitudinal studies with truncation by death or other intercurrent events

Intercurrent events, such as treatment switching, rescue medication, dropout, or truncation by death, frequently complicate intention-to-treat analyses in randomized clinical trials. Existing causal inference frameworks typically target hypothetical or principal stratum estimands (e.g., survivor average causal effects), which rely on unverifiable assumptions and can be sensitive to unmeasured confounders or positivity violations. We propose a novel approach that mitigates this sensitivity by using only information measured prior to the intercurrent event. Our key idea is to compare treated and untreated individuals, matched on baseline covariates, at the most recent time point before either experiences an intercurrent event. We call these contrasts Pairwise Last Observation Time (PLOT) estimands. PLOT estimands are identified in randomized trials without structural assumptions, even under severe positivity violations. Although PLOT-based tests may theoretically be susceptible to residual selection bias, we show this bias vanishes under standard conditions and remains negligible in extensive simulations. We develop asymptotically efficient, model-free tests and treatment effect estimators using data-adaptive nuisance parameter estimation. We evaluate performance via simulation and apply the method to re-analyze the DEVOTE trial, affected by truncation by death. PLOT offers a robust, data-driven alternative for evaluating treatment efficacy in the presence of complex intercurrent events.

stat.ME↗

arXiv2025

Causal machine learning for high-dimensional mediation analysis using interventional effects mapped to a target trial

Causal mediation analysis examines causal pathways linking exposures to disease. The estimation of interventional effects, which are mediation estimands that overcome certain identifiability problems of natural effects, has been advanced through causal machine learning methods, particularly for high-dimensional mediators. Recently, it has been proposed interventional effects can be defined in each study by mapping to a target trial assessing specific hypothetical mediator interventions. This provides an appealing framework to directly address real-world research questions about the extent to which such interventions might mitigate an increased disease risk in the exposed. However, existing estimators for interventional effects mapped to a target trial rely on singly-robust parametric approaches, limiting their applicability in high-dimensional settings. Building upon recent developments in causal machine learning for interventional effects, we address this gap by developing causal machine learning estimators for three interventional effect estimands, defined by target trials assessing hypothetical interventions inducing distinct shifts in joint mediator distributions. These estimands are motivated by a case study within the Longitudinal Study of Australian Children, used for illustration, which assessed how intervening on high inflammatory burden and other non-inflammatory adverse metabolomic markers might mitigate the adverse causal effect of overweight or obesity on high blood pressure in adolescence. We develop one-step and (partial) targeted minimum loss-based estimators based on efficient influence functions of those estimands, demonstrating they are root-n consistent, efficient, and multiply robust under certain conditions.

stat.ME↗

arXiv2025

Robust Covariate Adjustment in Multi-Center Randomized Trials

Augmented inverse probability weighting and G-computation with canonical generalized linear models have become increasingly popular for estimating the average treatment effect (ATE) in randomized experiments. These methods leverage outcome prediction models to adjust for imbalances in baseline covariates across treatment arms, improving power compared to unadjusted analyses, while controlling Type I error, even when models are misspecified. In multi-center trials they are often implemented without accounting for clustering by centers. We investigate how ignoring center-level correlation can impair estimation, degrade coverage of confidence intervals, and obscure interpretation. We find these issues to be especially acute for estimators of counterfactual means, as shown through simulations and clarified via theoretical arguments. To address these challenges, we develop semiparametric efficient estimators of counterfactual means and ATE defined for a randomly sampled center and patient. These estimators leverage outcome prediction models to improve efficiency yet retain large-sample unbiasedness under model misspecification. We further introduce an inference framework, inspired by random-effects meta-analysis, tailored to settings with many small centers. Incorporating center effects into the prediction models yields substantial efficiency gains, particularly when treatment effects vary across centers. Simulations and application to the WASH Benefits Bangladesh trial illustrate strong finite-sample performance of the proposed methods.

stat.ME↗

arXiv2025

Integration of aggregated data in causally interpretable meta-analysis by inverse weighting

Obtaining causally interpretable meta-analysis results is challenging when there are differences in the distribution of effect modifiers between eligible trials. To overcome this, recent work on transportability methods has considered standardizing results of individual studies over the case-mix of a target population, prior to pooling them as in a classical random-effect meta-analysis. One practical challenge, however, is that case-mix standardization often requires individual participant data (IPD) on outcome, treatments and case-mix characteristics to be fully accessible in every eligible study, along with IPD case-mix characteristics for a random sample from the target population. In this paper, we aim to develop novel strategies to integrate aggregated-level data from eligible trials with non-accessible IPD into a causal meta-analysis, by extending moment-based methods frequently used for population-adjusted indirect comparison in health technology assessment. Since valid inference for these moment-based methods by M-estimation theory requires additional aggregated data that are often unavailable in practice, computational methods to address this concern are also developed. We assess the finite-sample performance of the proposed approaches by simulated data, and then apply these on real-world clinical data to investigate the effectiveness of risankizumab versus ustekinumab among patients with moderate to severe psoriasis.

stat.ME↗

arXiv2024

Causal machine learning for heterogeneous treatment effects in the presence of missing outcome data

When estimating heterogeneous treatment effects, missing outcome data can complicate treatment effect estimation, causing certain subgroups of the population to be poorly represented. In this work, we discuss this commonly overlooked problem and consider the impact that missing at random (MAR) outcome data has on causal machine learning estimators for the conditional average treatment effect (CATE). We propose two de-biased machine learning estimators for the CATE, the mDR-learner and mEP-learner, which address the issue of under-representation by integrating inverse probability of censoring weights into the DR-learner and EP-learner respectively. We show that under reasonable conditions, these estimators are oracle efficient, and illustrate their favorable performance through simulated data settings, comparing them to existing CATE estimators, including comparison to estimators which use common missing data techniques. We present an example of their application using the GBSG2 trial, exploring treatment effect heterogeneity when comparing hormonal therapies to non-hormonal therapies among breast cancer patients post surgery, and offer guidance on the decisions a practitioner must make when implementing these estimators.

stat.ML↗

arXiv2024

Debiasing Synthetic Data Generated by Deep Generative Models

While synthetic data hold great promise for privacy protection, their statistical analysis poses significant challenges that necessitate innovative solutions. The use of deep generative models (DGMs) for synthetic data generation is known to induce considerable bias and imprecision into synthetic data analyses, compromising their inferential utility as opposed to original data analyses. This bias and uncertainty can be substantial enough to impede statistical convergence rates, even in seemingly straightforward analyses like mean calculation. The standard errors of such estimators then exhibit slower shrinkage with sample size than the typical 1 over root-$n$ rate. This complicates fundamental calculations like p-values and confidence intervals, with no straightforward remedy currently available. In response to these challenges, we propose a new strategy that targets synthetic data created by DGMs for specific data analyses. Drawing insights from debiased and targeted machine learning, our approach accounts for biases, enhances convergence rates, and facilitates the calculation of estimators with easily approximated large sample variances. We exemplify our proposal through a simulation study on toy data and two case studies on real-world data, highlighting the importance of tailoring DGMs for targeted data analysis. This debiasing strategy contributes to advancing the reliability and applicability of synthetic data in statistical inference.

stat.ML↗

arXiv2024

Chasing Shadows: How Implausible Assumptions Skew Our Understanding of Causal Estimands

The ICH E9 (R1) addendum on estimands, coupled with recent advancements in causal inference, has prompted a shift towards using model-free treatment effect estimands that are more closely aligned with the underlying scientific question. This represents a departure from traditional, model-dependent approaches where the statistical model often overshadows the inquiry itself. While this shift is a positive development, it has unintentionally led to the prioritization of an estimand's ability to perfectly answer the key scientific question over its practical learnability from data under plausible assumptions. We illustrate this by scrutinizing assumptions in the recent clinical trials literature on principal stratum estimands, demonstrating that some popular assumptions are not only implausible but often inevitably violated. We advocate for a more balanced approach to estimand formulation, one that carefully considers both the scientific relevance and the practical feasibility of estimation under realistic conditions.

stat.ME↗

arXiv2024

Two Stage Least Squares with Time-Varying Instruments: An Application to an Evaluation of Treatment Intensification for Type-2 Diabetes

As longitudinal data becomes more available in many settings, policy makers are increasingly interested in the effect of time-varying treatments (e.g. sustained treatment strategies). In settings such as this, the preferred analysis techniques are the g-methods, however these require the untestable assumption of no unmeasured confounding. Instrumental variable analyses can minimise bias through unmeasured confounding. Of these methods, the Two Stage Least Squares technique is one of the most well used in Econometrics, but it has not been fully extended, and evaluated, in full time-varying settings. This paper proposes a robust two stage least squares method for the econometric evaluation of time-varying treatment. Using a simulation study we found that, unlike standard two stage least squares, it performs relatively well across a wide range of circumstances, including model misspecification. It compares well with recent time-varying instrument approaches via g-estimation. We illustrate the methods in an evaluation of treatment intensification for Type-2 Diabetes Mellitus, exploring the exogeneity in prescribing preferences to operationalise a time-varying instrument.

stat.ME↗

arXiv2024

Instrumental Variable methods to target Hypothetical Estimands with longitudinal repeated measures data: Application to the STEP 1 trial

The STEP 1 randomized trial evaluated the effect of taking semaglutide vs placebo on body weight over a 68 week duration. As with any study evaluating an intervention delivered over a sustained period, non-adherence was observed. This was addressed in the original trial analysis within the Estimand Framework by viewing non-adherence as an intercurrent event. The primary analysis applied a treatment policy strategy which viewed it as an aspect of the treatment regimen, and thus made no adjustment for its presence. A supplementary analysis used a hypothetical strategy, targeting an estimand that would have been realised had all participants adhered, under the assumption that no post-baseline variables confounded adherence and change in body weight. In this paper we propose an alternative Instrumental Variable method to adjust for non-adherence which does not rely on the same `unconfoundedness' assumption and is less vulnerable to positivity violations (e.g., it can give valid results even under conditions where non-adherence is guaranteed). Unlike many previous Instrumental Variable approaches, it makes full use of the repeatedly measured outcome data, and allows for a time-varying effect of treatment adherence on a participant's weight. We show that it provides a natural vehicle for defining two distinct hypothetical estimands: the treatment effect if all participants would have adhered to semaglutide, and the treatment effect if all participants would have adhered to both semaglutide and placebo. When applied to the STEP 1 study, they both suggest a sustained, slowly decaying weight loss effect of semaglutide treatment.

stat.ME↗

arXiv2024

The Real Deal Behind the Artificial Appeal: Inferential Utility of Tabular Synthetic Data

Recent advances in generative models facilitate the creation of synthetic data to be made available for research in privacy-sensitive contexts. However, the analysis of synthetic data raises a unique set of methodological challenges. In this work, we highlight the importance of inferential utility and provide empirical evidence against naive inference from synthetic data, whereby synthetic data are treated as if they were actually observed. Before publishing synthetic data, it is essential to develop statistical inference tools for such data. By means of a simulation study, we show that the rate of false-positive findings (type 1 error) will be unacceptably high, even when the estimates are unbiased. Despite the use of a previously proposed correction factor, this problem persists for deep generative models, in part due to slower convergence of estimators and resulting underestimation of the true standard error. We further demonstrate our findings through a case study.

cs.LG↗

arXiv2024

On Weighted Orthogonal Learners for Heterogeneous Treatment Effects

Motivated by applications in personalized medicine and individualized policymaking, there is a growing interest in techniques for quantifying treatment effect heterogeneity in terms of the conditional average treatment effect (CATE). Some of the most prominent methods for CATE estimation developed in recent years are T-Learner, DR-Learner and R-Learner. The latter two were designed to improve on the former by being Neyman-orthogonal. However, the relations between them remain unclear, and likewise the literature remains vague on whether these learners converge to a useful quantity or (functional) estimand when the underlying optimization procedure is restricted to a class of functions that does not include the CATE. In this article, we provide insight into these questions by discussing DR-Learner and R-Learner as special cases of a general class of weighted Neyman-orthogonal learners for the CATE, for which we moreover derive oracle bounds. Our results shed light on how one may construct Neyman-orthogonal learners with desirable properties, on when DR-Learner may be preferred over R-Learner (and vice versa), and on novel learners that may sometimes be preferable to either of these. Theoretical findings are confirmed using results from simulation studies on synthetic data, as well as an application in critical care medicine.

stat.ME↗

arXiv2024

Causal machine learning methods and use of cross-fitting in settings with high-dimensional confounding

Observational epidemiological studies commonly seek to estimate the causal effect of an exposure on an outcome. Adjustment for potential confounding bias in modern studies is challenging due to the presence of high-dimensional confounding, which occurs when there are many confounders relative to sample size or complex relationships between continuous confounders and exposure and outcome. Doubly robust methods such as Augmented Inverse Probability Weighting (AIPW) and Targeted Maximum Likelihood Estimation (TMLE) have the potential to address these challenges, using data-adaptive approaches and cross-fitting, but despite recent advances limited evaluation and guidance are available on their implementation in realistic settings where high-dimensional confounding is present. Motivated by an early-life cohort study, we conducted an extensive simulation study to compare the relative performance of AIPW and TMLE using data-adaptive approaches for estimating the average causal effect (ACE). We evaluated the benefits of using cross-fitting with a varying number of folds, as well as the impact of using a reduced versus full (larger, more diverse) library in the Super Learner ensemble learning approach used for implementation. We found that AIPW and TMLE performed similarly in most cases for estimating the ACE, but TMLE was more stable. Cross-fitting improved the performance of both methods, but was more important for variance estimation and coverage than for point estimates, with the number of folds a less important consideration. Using a full Super Learner library was important to reduce bias and variance in complex scenarios typical of modern health research studies.

stat.ME↗

arXiv2024

Assumption-Lean Quantile Regression

Quantile regression is a powerful tool for detecting exposure-outcome associations given covariates across different parts of the outcome's distribution, but has two major limitations when the aim is to infer the effect of an exposure. Firstly, the exposure coefficient estimator may not converge to a meaningful quantity when the model is misspecified, and secondly, variable selection methods may induce bias and excess uncertainty, rendering inferences biased and overly optimistic. In this paper, we address these issues via partially linear quantile regression models which parametrize the conditional association of interest, but do not restrict the association with other covariates in the model. We propose consistent estimators for the unknown model parameter by mapping it onto a nonparametric main effect estimand that captures the (conditional) association of interest even when the quantile model is misspecified. This estimand is estimated using the efficient influence function under the nonparametric model, allowing for the incorporation of data-adaptive procedures such as variable selection and machine learning. Our approach provides a flexible and reliable method for detecting associations that is robust to model misspecification and excess uncertainty induced by variable selection methods. The proposal is illustrated using simulation studies and data on annual health care costs associated with excess body weight.

stat.ME↗

arXiv2024

Automated, efficient and model-free inference for randomized clinical trials via data-driven covariate adjustment

In 2023, the U.S. Food and Drug Administration issued guidance for adjustment of covariates in randomized clinical trials, emphasizing its role in enhancing precision and power through prognostic baseline variables. Despite its potential, many trials underutilize this method partly due to challenges in pre-specifying optimal baseline covariates and their functional forms. We explore the potential of automated, data-adaptive methods-including stepwise regression, Lasso and flexible machine learning algorithms-for covariate adjustment, addressing the challenge of pre-specification. Our approach ensures valid and interpretable treatment effect estimates and standard errors, even when outcome models are misspecified or biased outcome predictions are used. This differs from most competing methods, which assume correctly specified models for consistent standard errors. Our estimators require cross-fitting for reliable standard error estimation, though it can be omitted when variable selection is used, provided the outcome model satisfies an ultra-sparsity assumption. As such, we arrive at simple estimators and standard errors for marginal treatment effects in randomized clinical trials (or similar studies like A/B-testing), exploiting data-adaptive predictions from prognostic baseline covariates, with little (or no) bias in finite samples even when predictions are biased. Empirical and methodological results demonstrate promise of automated covariate adjustment for improving statistical power of trial analyses.

stat.ME↗

arXiv2024

Optimally weighted average derivative effects

Weighted average derivative effects (WADEs) are nonparametric estimands with uses in economics and causal inference. Debiased WADE estimators typically require learning the conditional mean outcome as well as a Riesz representer (RR) that characterises the requisite debiasing corrections. RR estimators for WADEs often rely on kernel estimators, introducing complicated bandwidth-dependant biases. In our work we propose a new class of RRs that are isomorphic to the class of WADEs and we derive the WADE weight that is optimal, in the sense of having minimum nonparametric efficiency bound. Our optimal WADE estimators require estimating conditional expectations only (e.g. using machine learning), thus overcoming the limitations of kernel estimators. Moreover, we connect our optimal WADE to projection parameters in partially linear models. We ascribe a causal interpretation to WADE and projection parameters in terms of so-called incremental effects. We propose efficient estimators for two WADE estimands in our class, which we evaluate in a numerical experiment and use to determine the effect of Warfarin dose on blood clotting function.

stat.ME↗

arXiv2023

Handling time-dependent exposures and confounders when estimating attributable fractions -- bridging the gap between multistate and counterfactual modeling

The population-attributable fraction (PAF) expresses the proportion of events that can be ascribed to a certain exposure in a certain population. It can be strongly time-dependent because either exposure incidence or excess risk may change over time. Competing events may moreover hinder the outcome of interest from being observed. Occurrence of either of these events may, in turn, prevent the exposure of interest. Estimation approaches therefore need to carefully account for the timing of events in such highly dynamic settings. The use of multistate models has been widely encouraged to eliminate preventable yet common types of time-dependent bias. Even so, it has been pointed out that proposed multistate modeling approaches for PAF estimation fail to fully eliminate such bias. In addition, assessing whether patients die from rather than with a certain exposure not only requires adequate modeling of the timing of events but also of their confounding factors. While proposed multistate modeling approaches for confounding adjustment may adequately accommodate baseline imbalances, unlike g-methods, these proposals are not generally equipped to handle time-dependent confounding. However, the connection between multistate modeling and g-methods (e.g. inverse probability of censoring weighting) for PAF estimation is not readily apparent. In this paper, we provide a weighting-based characterization of both approaches to illustrate this connection, to pinpoint current shortcomings of multistate modeling, and to enhance intuition into simple modifications to overcome these. R code is made available to foster the uptake of g-methods for PAF estimation.

stat.ME↗