434 papers
This paper introduces a class of robust regularised M-estimators for high-dimensional regression that achieves optimal convergence rates and variable selection consistency under minimal moment conditions (finite ), outperforming existing methods in both simulation and real-world genomic applications when dealing with heavy-tailed, skewed, or contaminated errors.
The paper proposes Sparse Convex Biclustering (SpaCoBi), a novel convex optimization method with a stability-based tuning criterion that effectively addresses noise and computational challenges in high-dimensional datasets, demonstrating superior accuracy and robustness compared to existing state-of-the-art biclustering techniques.
This paper demonstrates that including composite quality ratings as covariates in regression models introduces a circularity bias that systematically attenuates the estimated effects of structural predictors, a methodological hazard confirmed through CMS hospital readmission data and Monte Carlo simulations.
This study demonstrates that perceived resource scarcity increases risky decision-making, particularly under high objective risk, by accelerating the drift rate toward the risky option as revealed through hierarchical drift diffusion modeling.
This paper presents an explainable, reproducible public-data framework for Medicare payment integrity that integrates rank-aggregated anomaly ensembles and conformal cost-reference bands to prioritize audit triage while distinguishing statistical anomalies from proof of misconduct.
This paper introduces a median-based effect size indicator for mathematics education research that offers a more intuitive and robust alternative to Cohen's d by comparing group values to medians, thereby reducing sensitivity to skewed distributions, outliers, and small sample sizes while better aligning with practical interpretations of student performance.
This paper introduces the HAIB-MEC framework, a hybrid machine learning–Bayesian system that integrates nonlinear predictive modeling with hierarchical uncertainty correction to significantly improve accuracy, reduce bias, and enhance reliability in health datasets affected by measurement error.
This paper introduces the Nonsense Dependence Index (NDI), a simple rank-based diagnostic defined as the difference between Kendall's and the square root of Bergsma–Dassios' , to effectively distinguish genuine monotone relationships from spurious associations driven by common trends or external factors.
This study compares SARIMA and LSTM models for forecasting Indonesian insurance comprehensive income, finding that while SARIMA better captures seasonal trends, both models exhibit limited accuracy, suggesting that future hybrid approaches and external variables are needed to improve forecasting performance.
This study evaluated propensity score inverse probability weighting (PS-IPW) and multiple imputation (MI) against complete case analysis for handling monotonic missing data in a pulmonary TB-HIV supplementation trial in Tanzania, finding that while both advanced methods outperformed traditional analysis in bias and efficiency, none revealed statistically significant treatment effects.