arXiv subjects

Eric J. Tchetgen Tchetgen

Publications and source records attributed to Eric J. Tchetgen Tchetgen.

At least 19 recordsLinked to original sources

arXiv2026

What does two-sample Mendelian randomization estimate when the exposure-outcome relationship is nonlinear?

Two-sample Mendelian randomization with summary statistics has become a popular MR design in Epidemiology. Its ratio estimate has an average causal effect interpretation only under strong untestable assumptions including linearity. We derive what the per-variant ratio, and the pooled and robust estimators built from it, estimate when a continuous exposure has a nonlinear effect, under two conditions on how genetic variation and unmeasured factors shape exposure: no unmeasured common effect modifier, and an exposure control function. Under either condition, each variant's ratio is a weighted average of the slope of the dose-response curve, with weights that depend on how that variant moves the distribution of exposure and that are nonnegative when the exposure distributions at different genotypes do not cross. Variants that shift everyone's exposure equally target nearly the same quantity; variants acting at particular doses or on the spread of exposure target different ones, some outside the range of any individual effect. Pooled estimates therefore have no fixed interpretation, heterogeneity tests and MR-Egger misread nonlinearity as pleiotropy, and summary statistics cannot reveal the problem, even when the dose-response curve is identifiable from individual-level data. For continuous exposures, two-sample estimates rest on a linearity assumption that should be stated and defended; individual-level exposure data resolve the problem and should be prioritized.

stat.ME↗

arXiv2026

A General Exposure-Mapping-Agnostic Framework for Causal Inference under Interference

We develop a general framework for design-based causal inference under interference in cluster experiments conducted via two-stage randomization on a network of interconnected units, without relying on exposure mapping assumptions, exclusion of cross-cluster interference, or Bernoulli treatment assignments. Within this framework, we establish a complete characterization of linear weighted estimators (LW) as defined by Godambe (1955) that achieve identification of various network causal effects under interference. This general class includes several new estimators with improved theoretical guarantees and superior finite-sample performance relative to existing approaches such as standard inverse-probability-of-treatment weighting. For most estimators in this class, we establish central limit theorems and conservative variance estimators, which allows us to describe the distinct asymptotic behavior exhibited by different weighting schemes potentially of interest. In particular, we study how randomization at the cluster-level affects the asymptotic behavior of various estimators, and we identify a subclass of cluster-agnostic LW estimators whose convergence rates are independent of the number of clusters and attain the optimal root-N rate, where N denotes the total number of units. Notably, for complete randomization we develop new techniques that may be of independent interest, both to establish a central limit theorem for sums of general dependent statistics and to construct conservative and bias-corrected variance estimators. We complement our theoretical results with extensive simulation studies that offer practical guidance on the choice of weighting method and experimental design under a wide range of interference structures.

stat.ME↗

arXiv2026

How should we select test-negative controls? A causal perspective in the era of multiplex respiratory testing

The test-negative design (TND) is widely used to estimate vaccine effectiveness (VE) for respiratory pathogens by comparing vaccination odds among test-positive cases versus test-negative controls. A central yet underexplored design element is which test-negative illnesses constitute valid controls. With rapid multiplex PCR panels, investigators can now identify specific non-focal pathogens among test-negative patients, allowing for better characterization of ``test-negative illness'', but also revealing a mixture of control outcomes that may each satisfy or violate causal assumptions. We synthesize recent causal identification results for the TND and show that they imply two distinct interpretations of control selection: 1) a sampling view in which controls represent the source population and 2) a bias-correction view in which controls function as negative control outcomes under equi-confounding. Building on these interpretations, we develop a framework for multiplex-informed control selection. We propose a taxonomy that distinguishes controls that serve primarily as exposure proxies (sharing unmeasured determinants of infection) from those that serve as testing proxies (sharing unmeasured determinants of care-seeking), derive implications for pathogen-specific and pooled estimators, and suggest three practical principles for control selection: vaccine irrelevance, avoidance of entanglement with other interventions, and testing-process comparability. We also formalize nuances introduced by multiplex panels, including co-detections and pan-negative episodes, and outline when standard pooled estimators remain valid versus when alternative estimators are needed. In simulations across 9 scenarios, we demonstrate violations concentrated in a single control pathogen can substantially bias pooled TND estimates, whereas a pre-specified pathogen screening estimator remained unbiased.

stat.ME↗

arXiv2026

Exploiting independence constraints for efficient estimation of bounds on causal effects in the presence of unmeasured confounding

Causal graphs may inform covariate adjustment for estimating causal effects and improve estimation efficiency by exploiting the graphical structure. In many applications, however, the target causal parameter may not be point-identified due to the presence of unmeasured confounding. Sensitivity analysis methods address this challenge by characterizing bounds on the causal parameter under varying assumptions about the magnitude or form of unmeasured confounding. We focus on semiparametric efficient estimation of causal effects in non-identifiable settings, assuming a known (or hypothesized) causal graph. We propose an influence function projection approach that exploits the conditional independence constraints implied by the graph to improve the efficiency of semiparametric estimators of upper and lower bounds on the average causal effect under a given sensitivity analysis model. Our approach applies across multiple sensitivity analysis frameworks and causal estimands, thereby connecting knowledge of graphical structure with the sensitivity analysis literature. We illustrate our approach through simulations and real data examples thought to be affected by unmeasured confounding, including the effect of labor training program on post-intervention earnings, and the effect of low ejection fraction on heart failure death.

stat.ME↗

arXiv2026

Doubly Robust and Efficient Calibration of Prediction Sets for Right-Censored Time-to-Event Outcomes

Our objective is to construct well-calibrated prediction sets for a time-to-event outcome subject to right-censoring with guaranteed coverage. Inspired by modern conformal inference, our approach avoids the need for a well-specified parametric or semiparametric survival model. Unlike existing conformal methods for survival data, which assume Type-I censoring with fully observed censoring times, we consider the more common right-censoring setting in which only the censoring time or only the event time is observed, whichever comes first. Under a standard conditional independence censoring condition, we propose and analyze several lower prediction bounds for the survival time of a future observation, including inverse-probability-of-censoring weighting, and its augmented version based on the semiparametric efficient influence function for the relevant marginal quantile of the outcome accounting for dependent censoring. We formally establish asymptotic coverage guarantees of the proposed methods, and demonstrate both theoretically and through empirical experiments, that the augmented approach substantially improves efficiency over all other proposed methods. Specifically, its coverage error bound is doubly robust, and therefore of second order, thus ensuring that it is asymptotically negligible relative to the coverage error of the other methods.

stat.ME↗

arXiv2026

The Multiplicative Instrumental Variable Model

The instrumental variable (IV) design is a common approach to address hidden confounding bias. For validity, an IV must impact the outcome only through its association with the treatment. In addition, IV identification has required a homogeneity condition such as monotonicity or no unmeasured common effect modifier between the additive effect of the treatment on the outcome, and that of the IV on the treatment. In this work, we introduce the Multiplicative Instrumental Variable Model (MIV), which encodes a condition of no multiplicative interaction between the instrument and an unmeasured confounder in the treatment propensity score model. Thus, the MIV provides a novel formalization of the core IV independence condition interpreted as independent mechanisms of action, by which the instrument and hidden confounders influence treatment uptake, respectively. As we formally establish, MIV provides nonparametric identification of the population average treatment effect on the treated (ATT) via a single-arm version of the classical Wald ratio IV estimand, for which we propose a novel class of estimators that are multiply robust and semiparametric efficient. Finally, we illustrate the methods in extended simulations and an application on the causal impact of a job training program on subsequent earnings.

stat.ME↗

arXiv2026

The Multiplicative Quasi-Instrumental Variable Model

We introduce the Multiplicative Quasi-Instrumental Variable (MQIV) model, a framework for causal inference with unmeasured confounding that leverages an instrument that may be imperfectly exogenous. We allow the candidate quasi-instrument to have a direct effect on the outcome not mediated by the treatment, thus violating the standard IV exclusion restriction. We establish nonparametric identification of the population average treatment effect on the treated (ATT) under a treatment model that is multiplicative with respect to the quasi-IV and the hidden confounder (Hernan and Robins, 2006). Such a multiplicative treatment model may arise naturally either when treatment occurs only if two independent instrument-driven and confounder-driven causal mechanisms are present; or alternatively, when an instrument's effect on treatment uptake is inherently heterogeneous and scales with a person's latent propensity, best capturing settings in which it is challenging for a given instrument to overcome a person's inherent lack of preference for the treatment in view. Importantly, as we establish, the MQIV model is simultaneously agnostic to treatment-effect heterogeneity with respect to hidden confounders and violation of the core IV exclusion restriction condition. Identification is achieved via a modified Wald ratio estimand, which corrects the bias due to the exclusion restriction violation, and we propose a new class of estimators that are multiply robust and semiparametric efficient. Finally, we evaluate the approach in extensive simulations and an application to evaluate the causal effect of having three or more children on mothers' labor-market engagement.

stat.ME↗

arXiv2025

Auto-Doubly Robust Estimation of Causal Effects on a Network

This paper develops new methods for causal inference in observational studies on a single large network of interconnected units, addressing two key challenges: long-range dependence among units and the presence of general interference. We introduce a novel network version of Augmented Inverse Propensity Weighted, which combines propensity score and outcome models defined on the network to achieve doubly robust identification and estimation of both direct and spillover causal effects. Under a network version of conditional ignorability, the proposed approach identifies the expected potential outcome for a unit given the treatment assignment vector for its network neighborhood up to a user-specified distance, while marginalizing over treatment assignments for the rest of the network. Under the union of two Markov assumptions--one governing the propensity score model and the other the outcome model--we propose a corresponding semiparametric estimator based on general parametric specifications of nuisance functions. In particular, we suggest a class of parametric auto-regression models motivated by the Markov assumptions (Besag, 1974). By combining a restricted interference assumption with the propensity score model, we establish a new doubly robust identification result for the expected potential outcome under a hypothetical intervention on the treatment assignment vector for the entire network. We formally prove that, under weak network dependence, our proposed estimators are asymptotically normal and we characterize the impact of model misspecification on the asymptotic variance. Extensive simulation studies highlight the practical relevance of our approach. We further demonstrate its application in an empirical analysis of the NNAHRAY study, evaluating the impact of incarceration on individual socioeconomic outcomes in Brooklyn, New York.

stat.ME↗

arXiv2025

A Multiplicative Instrumental Variable Model for Data Missing Not-at-Random

Instrumental variable (IV) methods offer a valuable approach to account for outcome data missing not-at-random. A valid missing data instrument is a measured factor which (i) predicts the nonresponse process and (ii) is independent of the outcome in the underlying population. For point identification, all existing IV methods for missing data including the celebrated Heckman selection model, a priori restrict the extent of selection bias on the outcome scale, therefore potentially understating uncertainty due to missing data. In this work, we introduce an IV framework which allows the degree of selection bias on the outcome scale to remain completely unrestricted. The new approach instead relies for identification on (iii) a key multiplicative selection model, which posits that the instrument and any hidden common correlate of selection and the outcome, do not interact on the multiplicative scale. Interestingly, we establish that any regular statistical functional of the missing outcome is nonparametrically identified under (i)-(iii) via a single-arm Wald ratio estimand reminiscent of the standard Wald ratio estimand in causal inference. For estimation and inference, we characterize the influence function for any functional defined on a nonparametric model for the observed data, which we leverage to develop semiparametric multiply robust IV estimators. Several extensions of the methods are also considered, including the important practical setting of polytomous and continuous instruments. Simulation studies illustrate the favorable finite sample performance of proposed methods, which we further showcase in an HIV study nested within a household health survey study we conducted in Mochudi, Botswana, in which interviewer characteristics are used as instruments to correct for selection bias due to dependent nonresponse in the HIV component of the survey study.

stat.ME↗

arXiv2025

Refining the Notion of No Anticipation in Difference-in-Differences Studies

We address an ambiguity in identification strategies using difference-in-differences, which are widely applied in empirical research, particularly in economics. The assumption commonly referred to as the "no-anticipation assumption" states that treatment has no effect on outcomes before its implementation. However, because standard causal models rely on a temporal structure in which causes precede effects, such an assumption seems to be inherently satisfied. This raises the question of whether the assumption is repeatedly stated out of redundancy or because the formal statements fail to capture the intended subject-matter interpretation. We argue that confusion surrounding the no-anticipation assumption arises from ambiguity in the intervention considered and that current formulations of the assumption are ambiguous. Therefore, new definitions and identification results are proposed.

stat.ME↗

arXiv2025

Identification and estimation of vaccine effectiveness in the test-negative design under equi-confounding

The test-negative design (TND) is widely used to evaluate vaccine effectiveness in real-world settings. In a TND study, individuals with similar symptoms who seek care are tested, and effectiveness is estimated by comparing vaccination histories of test-positive cases and test-negative controls. The TND is often justified on the grounds that it reduces confounding due to unmeasured health-seeking behavior, although this has not been formally described using potential outcomes. At the same time, concerns persist that conditioning on test receipt can introduce selection bias. We provide a formal justification of the TND under an assumption of odds ratio equi-confounding, where unmeasured confounders affect test-positive and test-negative individuals equivalently on the odds ratio scale. Health-seeking behavior is one plausible example. We also show that these results hold under the outcome-dependent sampling used in TNDs. We discuss the design implications of the equi-confounding assumption and provide alternative estimators for the marginal risk ratio among the vaccinated under equi-confounding, including outcome modeling and inverse probability weighting estimators as well as a semiparametric estimator that is doubly robust. When equi-confounding does not hold, we suggest a straightforward sensitivity analysis that parameterizes the magnitude of the deviation on the odds ratio scale. A simulation study evaluates the empirical performance of our proposed estimators under a wide range of scenarios. Finally, we discuss broader uses of test-negative outcomes to de-bias cohort studies in which testing is triggered by symptoms.

stat.ME↗

arXiv2025

Inference on Nonlinear Counterfactual Functionals under a Multiplicative IV Model

Instrumental variable (IV) methods play a central role in causal inference, particularly in settings where treatment assignment is confounded by unobserved variables. IV methods have been extensively developed in recent years and applied across diverse domains, from economics to epidemiology. In this work, we study the recently introduced multiplicative IV (MIV) model and demonstrate its utility for causal inference beyond the average treatment effect. In particular, we show that it enables identification and inference for a broad class of counterfactual functionals characterized by moment equations. This includes, for example, inference on quantile treatment effects. We develop methods for efficient and multiply robust estimation of such functionals, and provide inference procedures with asymptotic validity. Experimental results demonstrate that the proposed procedure performs well even with moderate sample sizes.

stat.ME↗

arXiv2025

Multiply Robust Conformal Risk Control with Coarsened Data

Conformal Prediction (CP) has recently received a tremendous amount of interest, leading to a wide range of new theoretical and methodological results for predictive inference with formal theoretical guarantees. However, the vast majority of CP methods assume that all units in the training data have fully observed data on both the outcome and covariates of primary interest, an assumption that rarely holds in practice. In reality, training data are often missing the outcome, a subset of covariates, or both on some units. In addition, time-to-event outcomes in the training set may be censored due to dropout or administrative end-of-follow-up. Accurately accounting for such coarsened data in the training sample while fulfilling the primary objective of well-calibrated conformal predictive inference, requires robustness and efficiency considerations. In this paper, we consider the general problem of obtaining distribution-free valid prediction regions for an outcome given coarsened training data. Leveraging modern semiparametric theory, we achieve our goal by deriving the efficient influence function of the quantile of the outcome we aim to predict, under a given semiparametric model for the coarsened data, carefully combined with a novel conformal risk control procedure. Our principled use of semiparametric theory has the key advantage of facilitating flexible machine learning methods such as random forests to learn the underlying nuisance functions of the semiparametric model. A straightforward application of the proposed general framework produces prediction intervals with stronger coverage properties under covariate shift, as well as the construction of multiply robust prediction sets in monotone missingness scenarios. We further illustrate the performance of our methods through various simulation studies.

math.ST↗

arXiv2025

On a Debiased and Semiparametric Efficient Changes-in-Changes Estimator

We present a novel extension of the influential changes-in-changes (CiC) framework of Athey and Imbens (2006) for estimating the average treatment effect on the treated (ATT) and distributional causal effects in panel data with unmeasured confounding. While CiC relaxes the parallel trends assumption in difference-in-differences (DiD), existing methods typically assume a scalar unobserved confounder and monotonic outcome relationships, and lack inference tools that accommodate continuous covariates flexibly. Motivated by empirical settings with complex confounding and rich covariate information, we make two main contributions. First, we establish nonparametric identification under relaxed assumptions that allow high-dimensional, non-monotonic unmeasured confounding. Second, we derive semiparametrically efficient estimators that are Neyman orthogonal to infinite-dimensional nuisance parameters, enabling valid inference even with machine learning-based estimation of nuisance components. We illustrate the utility of our approach in an empirical analysis of mass shootings and U.S. electoral outcomes, where key confounders, such as political mobilization or local gun culture, are typically unobserved and challenging to quantify.

stat.ME↗

arXiv2025

Partial Identification of Causal Effects for Endogenous Continuous Treatments

No unmeasured confounding is a common assumption when reasoning about counterfactual outcomes, but such an assumption may not be plausible in observational studies. Sensitivity analysis is often employed to assess the robustness of causal conclusions to unmeasured confounding, but existing methods are predominantly designed for binary treatments. In this paper, we provide natural extensions of two extensively used sensitivity frameworks -- the Rosenbaum and Marginal sensitivity models -- to the setting of continuous exposures. Our generalization replaces scalar sensitivity parameters with sensitivity functions that vary with exposure level, enabling richer modeling and sharper identification bounds. We develop a unified pseudo-outcome regression formulation for bounding the counterfactual dose-response curve under both models, and propose corresponding nonparametric estimators which have second order bias. These estimators accommodate modern machine learning methods for obtaining nuisance parameter estimators, which are shown to achieve $L^2$- consistency, minimax rates of convergence under suitable conditions. Our resulting estimators of bounds for the counterfactual dose-response curve are shown to be consistent and asymptotic normal allowing for a user-specified bound on the degree of uncontrolled exposure endogeneity. We also offer a geometric interpretation that relates the Rosenbaum and Marginal sensitivity model and guides their practical usage in global versus targeted sensitivity analysis. The methods are validated through simulations and a real-data application on the effect of second-hand smoke exposure on blood lead levels in children.

stat.ME↗

arXiv2025

Fortified Proximal Causal Inference with Many Invalid Proxies

Causal inference from observational data often relies on the assumption of no unmeasured confounding, an assumption frequently violated in practice due to unobserved or poorly measured covariates. Proximal causal inference (PCI) offers a promising framework for addressing unmeasured confounding using a pair of outcome and treatment confounding proxies. However, existing PCI methods typically assume all specified proxies are valid, which may be unrealistic and is untestable without extra assumptions. In this paper, we develop a semiparametric approach for a many-proxy PCI setting that accommodates potentially invalid treatment confounding proxies. We introduce a new class of fortified confounding bridge functions and establish nonparametric identification of the population average treatment effect (ATE) under the assumption that at least $γ$ out of $K$ candidate treatment confounding proxies are valid, for any $γ\leq K$ set by the analyst without requiring knowledge of which proxies are valid. We establish a local semiparametric efficiency bound and develop a class of multiply robust, locally efficient estimators for the ATE. These estimators are thus simultaneously robust to invalid treatment confounding proxies and model misspecification of nuisance parameters. The proposed methods are evaluated through simulation and applied to assess the effect of right heart catheterization in critically ill patients.

stat.ME↗

arXiv2025

Regression-based proximal causal inference for right-censored time-to-event data

Unmeasured confounding is one of the major concerns in causal inference from observational data. Proximal causal inference (PCI) is an emerging methodological framework to detect and potentially account for confounding bias by carefully leveraging a pair of negative control exposure (NCE) and outcome (NCO) variables, also known as treatment and outcome confounding proxies. Although regression-based PCI is well developed for binary and continuous outcomes, analogous PCI regression methods for right-censored time-to-event outcomes are currently lacking. In this paper, we propose a novel two-stage regression PCI approach for right-censored survival data under an additive hazard structural model. We provide theoretical justification for the proposed approach tailored to different types of NCOs, including continuous, count, and right-censored time-to-event variables. We illustrate the approach with an evaluation of the effectiveness of right heart catheterization among critically ill patients using data from the SUPPORT study. Our method is implemented in the open-access R package 'pci2s'.

stat.ME↗

arXiv2025

Beyond Fixed Restriction Time: Adaptive Restricted Mean Survival Time Methods in Clinical Trials

Restricted mean survival time (RMST) offers a compelling nonparametric alternative to hazard ratios for right-censored time-to-event data, particularly when the proportional hazards assumption is violated. By capturing the total event-free time over a specified horizon, RMST provides an intuitive and clinically meaningful measure of absolute treatment benefit. Nonetheless, selecting the restriction time $L$ poses challenges: choosing a small $L$ can overlook late-emerging benefits, whereas a large $L$, often underestimated in its impact, may inflate variance and undermine power. We propose a novel data-driven, adaptive procedure that identifies the optimal restriction time $L^*$ from a continuous range by maximizing a criterion balancing effect size and estimation precision. Consequently, our procedure is particularly useful when the pattern of the treatment effect is unknown at the design stage. We provide a rigorous theoretical foundation that accounts for variability introduced by adaptively choosing $L^*$. To address nonregular estimation under the null, we develop two complementary strategies: a convex-hull-based estimator, and a penalized approach that further enhances power. Additionally, when restriction time candidates are defined on a discrete grid, we propose a procedure that surprisingly incurs no asymptotic penalty for selection, thus achieving oracle performance. Extensive simulations across realistic survival scenarios demonstrate that our method outperforms traditional RMST analyses and the log-rank test, achieving superior power while maintaining nominal Type I error rates. In a phase III pancreatic cancer trial with transient treatment effects, our procedure uncovers clinically meaningful benefits that standard methods overlook. Our methods are implemented in the R package AdaRMST.

stat.ME↗