427 papers
This study quantifies the impact of population skewness on the sample size required for the Central Limit Theorem to ensure normality, deriving a conservative quadratic regression model that reveals standard rules of thumb are often inadequate for asymmetric data, particularly when discreteness or severe kurtosis are present.
This study evaluates five practical address-matching approaches for assigning Unique Property Reference Numbers (UPRNs) to Early Years Provider records in England, finding that while linkage coverage varies significantly, routine inclusion of UPRNs in official registers is essential for accurate spatial identification and effective service planning.
This paper presents an integrated wildfire ignition modeling framework that distinguishes between utility and non-utility sources using separate inhomogeneous Poisson point processes, revealing distinct spatial drivers for each to enable more targeted regional risk assessment and mitigation in California.
This study employs hexagonal tessellation and spatial statistics to analyze the distribution of public transportation stops in Culiacán, Mexico, revealing a non-random, hierarchical pattern of high-density central cores and low-density peripheral sectors that highlights spatial inequities in urban accessibility.
This paper proposes three deep learning-based algorithms to numerically solve high-dimensional mean-field stochastic optimal control problems derived via the stochastic maximum principle, demonstrating their accuracy and efficiency through applications to mean-variance portfolio selection.
This study introduces a bidirectional, historical, and peer-calibrated audit framework that successfully identifies and prioritizes internally inconsistent outcomes in the July 2026 Webometrics university rankings, distinguishing genuine anomalies from noise without inferring institutional quality or manipulation.
This paper introduces the Discrete Past Geometric Vitality Function (PGVF) as a multiplicative analogue of the classical past vitality function for discrete lifetimes, establishing its theoretical properties, proving its ability to uniquely characterize distributions, and proposing a nonparametric estimator validated through simulations and real-data applications.
This paper introduces a reproducible multi-task deep learning benchmark using a novel ResNet-FT-Transformer architecture with Cross-Attention Hydration to jointly predict children's climate hazard exposure and vulnerability from UNICEF data, demonstrating that while gradient-boosted ensembles remain competitive on small tabular datasets, the proposed model offers a unified, interpretable framework for guiding child-sensitive disaster risk reduction.
This paper demonstrates that FDA drug inspection classifications suffer from severe reporting bias, where failing inspections are recorded less frequently and with significant delays compared to passing ones, leading to substantial performance degradation in machine learning models and monitoring metrics that can only be partially mitigated by specific statistical adjustments or resolved by publishing the posting date.
This study demonstrates that while data leakage and post-outcome predictors can artificially inflate depression classification performance, rigorous leakage-controlled validation reveals that complex machine-learning algorithms offer little predictive advantage over simple logistic regression.