arXiv subjects

Herbert P. Susmann

Publications and source records attributed to Herbert P. Susmann.

4 recordsLinked to original sources

arXiv2026

Non-overlap Average Treatment Effect Bounds

The average treatment effect (ATE), the mean difference in potential outcomes under treatment and control, is a canonical causal effect. Overlap, which says that all subjects have non-zero probability of either treatment status, is necessary to identify and estimate the ATE. When overlap fails, the standard solution is to change the estimand, and target a trimmed effect in a subpopulation satisfying overlap. When the outcome is bounded, we demonstrate that this compromise is unnecessary. We derive non-overlap bounds: partial identification bounds on the ATE that do not require overlap. The bounds have width proportional to the size of the non-overlap subpopulation, making them informative in common scenarios when overlap violations are limited. Since the bounds are non-smooth functionals, we derive smooth approximations amenable to semiparametric efficiency theory and propose a Targeted Minimum Loss-Based estimator that is $\sqrt{n}$-consistent and asymptotically normal under nonparametric conditions. A multiplier bootstrap procedure yields uniformly valid confidence sets across all non-overlap subpopulation sizes and smoothing parameters, allowing researchers to report the tightest valid interval. Formally, we compare non-overlap confidence intervals to confidence intervals based on point estimation across multiple overlap regimes. We illustrate the method via simulation studies and real-world data applications.

stat.ME↗

arXiv2026

The Counterfactual Combine: A Causal Framework for Player Evaluation

Evaluating sports players based on their performance shares core challenges with evaluating healthcare providers based on patient outcomes. Drawing on recent advances in healthcare provider profiling, we cast sports player evaluation within a rigorous causal inference framework and define a flexible class of causal player evaluation estimands. Using stochastic interventions, we compare player success rates on repeated tasks (such as field goal attempts or plate appearance) to counterfactual success rates had those same attempts been randomly reassigned to players according to prespecified reference distributions. This setup encompasses direct and indirect standardization parameters familiar from healthcare provider profiling, and we additionally propose a "performance above random replacement" estimand designed for interpretability in sports settings. We develop doubly robust estimators for these evaluation metrics based on modern semiparametric statistical methods, with a focus on Targeted Minimum Loss-based Estimation, and incorporate machine learning methods to capture complex relationships driving player performance. We illustrate our framework in detailed case studies of field goal kickers in the National Football League and batters in Major League Baseball, highlighting how different causal estimands yield distinct interpretations and insights about player performance.

stat.AP↗

arXiv2025

Computationally and statistically efficient estimation of time-smoothed counterfactual curves

Longitudinal causal inference is concerned with defining, identifying, and estimating the effect of a time-varying intervention on a time-varying outcome that is indexed by a follow-up time. In an observational study, Robins's generalized g-formula can identify causal effects induced by a broad class of time-varying interventions. Various methods for estimating the generalized g-formula have been posed for different outcome types, such as a failure event indicator by a specified time (e.g. mortality by 5 year follow-up), as well as continuous or dichotomous/multi-valued outcomes measures at a specified time (e.g. blood pressure in mm/hg or an indicator of high blood pressure at 5-year follow-up). Multiply-robust, data-adaptive estimators leverage flexible nonparametric estimation algorithms while allowing for statistical inference. However, extant methods do not accommodate time-smoothing when multiple outcomes are measured over time, which can lead to substantial loss of precision. We propose a novel multiply-robust estimator of the generalized g-formula that accommodates time-smoothing over numerous available outcome measures. Our approach accommodates any intervention that can be described as a Longitudinal Modified Treatment Policy, a flexible class suitable for binary, multi-valued, and continuous longitudinal treatments. Our method produces an estimate of the effect curve: the causal effect of the intervention on the outcome at each measurement time, taking into account censoring and non-monotonic outcome missingness patterns. In simulations we find that the proposed algorithm outperforms extant multiply-robust approaches for effect curve estimation in scenarios with high degrees of outcome missingness and when there is strong confounding. We apply the method to study longitudinal effects of union membership on wages.

stat.ME↗

arXiv2025

Asymptotically Efficient Data-adaptive Penalized Shrinkage Estimation with Application to Causal Inference

A rich literature exists on constructing non-parametric estimators with optimal asymptotic properties. In addition to asymptotic guarantees, it is often of interest to design estimators with desirable finite-sample properties; such as reduced mean-squared error of a large set of parameters. We provide examples drawn from causal inference where this may be the case, such as estimating a large number of group-specific treatment effects. We show how finite-sample properties of non-parametric estimators, particularly their variance, can be improved by careful application of penalization. Given a target parameter of interest we derive a novel penalized parameter defined as the solution to an optimization problem that balances fidelity to the original parameter against a penalty term. By deriving the non-parametric efficiency bound for the penalized parameter, we are able to propose simple data-adaptive choices for the L1 and L2 tuning parameters designed to minimize finite-sample mean-squared error while preserving optimal asymptotic properties. The L1 and L2 penalization amounts to an adjustment that can be performed as a post-processing step applied to any asymptotically normal and efficient estimator. We show in extensive simulations that this adjustment yields estimators with lower MSE than the unpenalized estimators. Finally, we apply our approach to estimate provider quality measures of kidney dialysis providers within a causal inference framework.

stat.ME↗