252 papers
This paper proposes Adaptive Bayesian Threshold Heuristic strategies for the partial-information secretary problem by integrating full-information optimal stopping theory with Bayesian updating via a Normal-Gamma conjugate prior, demonstrating superior performance over maximum likelihood estimation methods, particularly under small sample sizes and weak prior information.
This paper proposes and evaluates the Cross-Fitted Contamination-Aware Generalized Empirical-Bayes Liu Shrinkage (CF-CABLS-MNL) estimator for Multinomial Logit models, a robust framework that integrates cross-fitted density-power-divergence, misclassification adjustment, and spectral shrinkage to significantly reduce mean squared error under multicollinearity and outliers, though empirical results indicate that while it excels in contaminated settings, direct regularization methods like Ridge regression may outperform it in clean or dense-data scenarios.
This paper proposes a model-based clustering framework for spherical and hyper-spherical data using elliptically symmetric distributions, specifically the elliptically symmetric angular Gaussian and spherical elliptically symmetric projected Cauchy distributions, which are estimated via the expectation–maximization algorithm and evaluated through simulations and real-world applications.
This study of 2,058 matches across six European leagues demonstrates that while relative performance indicators (team–opponent differences) are more effective than absolute indicators in predicting match outcomes, the most accurate predictive model is achieved by integrating both absolute and relative metrics.
This paper introduces the two-parameter Odd Log-Logistic Rayleigh (OLLR) distribution as a flexible extension of the Rayleigh model, deriving its statistical properties and demonstrating its superior performance in modeling lifetime data through applications on two real-world datasets.
This review synthesizes evidence from thirty studies across multiple countries to evaluate the design, performance, and equity implications of learning analytics and early warning systems for mathematics achievement, highlighting their predictive potential while identifying critical gaps in algorithmic fairness, cross-country comparability, and the integration of domain-specific diagnostic insights.
This paper proposes a Bayesian framework for target-domain interventional SHAP under covariate shift that derives exact posterior distributions and risk bounds to quantify uncertainty and optimize selective action, demonstrating through simulations and real-world data that this approach significantly reduces estimation error and opportunity loss compared to traditional methods, particularly when source and target distributions exhibit low overlap.
This paper proposes a comprehensive taxonomy for factorial cluster-randomised trial designs, drawing on multistratum concepts from agricultural and industrial research to classify existing clinical examples, illustrate ten design variants using a theoretical obesity intervention, and highlight practical challenges for optimising multilevel healthcare interventions.
This study utilizes IoT sensor data and advanced statistical modeling to quantify and project solid waste generation in Bukavu, DRC, revealing significant spatial and demographic disparities in production rates and providing evidence-based insights to optimize collection strategies and prioritize interventions in the city's challenging topographical and infrastructural context.
This paper introduces a double-threshold cascade model on random hypergraphs that captures asymmetric adoption and abandonment barriers, revealing how the interplay between distinct thresholds and hyperedge size heterogeneity induces bistability and discontinuous phase transitions, a framework validated by both analytical theory and empirical simulations.