selection bias correction

Accurate estimation and inference for the average treatment effect (ATE) in multi-covariate randomized controlled trials (RCTs) remain challenging, particularly under high-dimensional covariates and small sample sizes. Method: Building on the Neyman finite-population framework, we propose a bias-corrected regression-adjustment estimator with cross-fitting and introduce, for the first time, an HC3-type heteroskedasticity-robust standard error tailored to high-dimensional settings. We rigorously derive first- and second-order stochastic expansions of the random component of regression-adjustment estimators, identifying the source of higher-order bias in conventional inference; leveraging this insight, we design a cross-fitting procedure to eliminate bias and extend HC3 standard errors to stratified experimental designs. Results: Simulations and reanalysis of Angrist et al. (2009)’s education RCT demonstrate that our method substantially improves estimation accuracy, confidence interval coverage, and statistical power—especially in small-sample and high-dimensional scenarios.

In observational causal inference, weighting methods mitigate covariate imbalance but often inflate variance estimates and yield overly conservative standard errors. This paper proposes augmenting weighted regression with main effects of covariates and their interactions with the treatment variable, integrated with residualization and parametric model augmentation to form a unified inferential framework. We establish, for the first time under design-based, model-based, and finite-sample-corrected superpopulation sampling assumptions, that this approach yields asymptotically valid and more precise standard errors. Theory, simulations, and multiple empirical applications demonstrate substantially narrower confidence intervals—on average 15–30% shorter—with improved inferential accuracy and robustness to both exact and approximately balanced weights. The key innovation lies in achieving simultaneous gains in statistical efficiency and asymptotic validity at minimal variance cost.

The conventional Copas–Jackson (C-J) bound assumes a monotonic relationship between the standard error of effect estimates and selection probability, limiting its applicability under realistic non-monotonic publication bias mechanisms. Method: We relax this strong assumption and propose a general framework for constructing worst-case sensitivity bounds under a broad nonparametric selection model class—permitting arbitrary (including non-monotonic) dependence between selection probability and estimation uncertainty. Our approach formulates bound construction as a nonlinear programming problem with linear constraints and develops an efficient numerical algorithm to compute tractable approximations. Contribution/Results: Simulation studies demonstrate robust performance across diverse publication bias scenarios. Empirical applications to two real meta-analyses show substantially improved detection of bias impact and enhanced inferential reliability. This work constitutes the first extension of C-J–type bounds to non-monotonic selection mechanisms, delivering a more general, robust, and practically feasible tool for sensitivity analysis of publication bias.

This study addresses the bias and variance in false discovery rate (FDR) estimation when relying solely on published p-values under misspecified publication bias models—such as the common assumption of a hard p < 0.05 threshold that may not reflect the true selection mechanism. The authors derive, for the first time, closed-form expressions for the bias and variance of FDR estimators under arbitrary publication bias models, thereby establishing a theoretical foundation for sensitivity analyses under model misspecification. By constructing general analytical expressions and validating them empirically using replication data from psychology and p-value distributions from medical journals, the work demonstrates that the proposed framework accurately characterizes the sources of estimation bias and effectively supports robustness assessment of FDR estimates.

This paper addresses the lack of a unified framework for assessing systematic error (bias) across causal and descriptive inference. We propose the first cross-paradigm, generalizable bias risk assessment method, integrating modeling assumptions, data-generating mechanisms, and inferential objectives to cover high-risk settings—including randomized controlled trials (RCTs), nonprobability sampling, and statistical extrapolation—beyond traditional medical RCT constraints. Our approach combines qualitative bias mapping, assumption sensitivity analysis, and standardized reporting criteria, mandating explicit documentation of untestable assumptions and model uncertainty. The framework has been adopted as a mandatory reporting requirement by leading journals and funding agencies, thereby enhancing the reliability, interpretability, and external validity of research findings. (132 words)

Current systematic review guidelines restrict the inclusion of adaptive designs due to concerns about bias, yet they overlook the joint influence of bias and information content. This work proposes “precision-weighted bias” as a novel metric, which accounts for each study’s unconditional bias scaled by its precision, thereby more accurately reflecting its contribution to overall meta-analytic bias. Theoretical derivation demonstrates that the total bias in a meta-analysis is in fact a precision-weighted average of individual study biases, rather than a simple arithmetic mean. Simulation studies further reveal that although adaptive designs may exhibit unweighted bias, their precision-weighted bias is often negligible—resulting in minimal impact on pooled estimates when included. These findings provide both theoretical justification and methodological support for the appropriate inclusion of adaptive designs in systematic reviews.

Measurement error in covariates is pervasive in epidemiology and can induce substantial bias in estimated exposure–outcome relationships, particularly when these associations are nonlinear; yet systematic strategies for correction remain limited. This study presents the first comprehensive evaluation—via blinded, multi-stage simulations—of the performance of six correction methods (pointwise and coefficient-level SIMEX, Bayesian inference, multiple imputation, and regression calibration) combined with four flexible modeling techniques (B-splines, penalized splines, fractional polynomials, and natural splines). Results demonstrate that pointwise SIMEX yields the most accurate and robust estimates overall, while penalized splines, fractional polynomials, and natural splines perform comparably and outperform B-splines. No single approach consistently dominates across all scenarios, underscoring the necessity of conducting sensitivity analyses to account for uncertainty in both measurement error correction and functional form specification.

This study addresses a key challenge in randomized controlled trials: how to effectively leverage covariate adjustment to improve the precision of average treatment effect estimation while satisfying regulatory requirements and ensuring statistical validity. The authors propose a prespecified, transparent, and reproducible covariate adjustment framework that, for the first time, integrates data-adaptive methods and machine learning into a regulatory-compliant analytical pipeline. By combining model-misspecification-robust estimation with semiparametric efficiency theory, the approach consistently outperforms unadjusted analyses without compromising causal interpretability or statistical validity. It substantially enhances estimation precision, increases statistical power, and yields narrower confidence intervals.