427 papers
This paper proposes the Clinical Risk-Weighted Score (CRWS), a novel metric that decouples the penalties for false negatives and false positives to better reflect clinical priorities, demonstrating through MIMIC-IV analysis that it significantly alters model rankings and reveals greater clinical advantages for top-performing algorithms compared to the traditional F1 score.
This paper proposes a practical framework using summary statistics to screen for skewness and heteroscedasticity via the coefficient of variation and log-scale variance ratio, enabling researchers to recover valid, more powerful parametric inference for small-sample clinical data where traditional normality tests fail and standard t-tests are deficient.
The paper introduces T_root, a novel closed-form, parameter-free statistic that achieves accurate size calibration and robust power for testing independence in contingency tables across a wide range of sparsity and marginal heterogeneity, effectively unifying and outperforming existing methods like Pearson's chi-square and the Cressie-Read statistic while providing a deterministic solution without the need for permutation or bootstrap.
This paper introduces the Generalized Moment-Transmuted Cauchy (GMTC) distribution, a flexible heavy-tailed model that overcomes the classical Cauchy distribution's limitation of non-existent moments by incorporating a shape parameter to control tail behavior and ensure finite moments, while providing a comprehensive analysis of its properties, estimation methods, and practical applications.
This systematic review and meta-analysis argues that the observed lower prevalence of allergies in farming environments is likely an artifact of sampling bias and healthy worker effects rather than evidence of a genuine protective causal relationship.
This study introduces an open-source R framework within the nlmixr2 ecosystem that leverages metaheuristic algorithms, particularly ant colony optimization and tabu search, to significantly outperform traditional stepwise methods in automating population pharmacokinetic model selection and identifying ground-truth models.
This systematic review evaluates how geospatial technologies are transforming household survey sampling frames in low- and middle-income countries to address outdated census limitations, identifying four key methodological approaches while highlighting persistent challenges in validation and implementation that require further comparative evidence and standardized protocols.
This study employs hierarchical Bayesian modeling on a public visual working memory dataset to demonstrate that memory precision decreases systematically with increased load, revealing substantial individual variability and showing that a nonlinear model outperforms linear alternatives in capturing these effects.
This paper introduces and validates the Clustered Logistic Factor with Random Effects (CLF-RE) framework as a computationally scalable multiple imputation method that effectively recovers incomplete, high-dimensional longitudinal binary data in electronic health records, significantly reducing bias in epidemiologic estimates compared to existing approaches.
This study utilizes an EM–Weibull mixture model applied to Peruvian National Household Survey data to estimate the first and second-use lifespans of 12 household appliance categories, revealing distinct ownership diffusion patterns and providing the first nationally representative assessment of appliance longevity and reuse in Peru from 2008 to 2024.