427 papers
This study demonstrates that rule-based automated auditing of statistical quality in university theses performs worse than chance due to fundamental lexical limitations, but integrating a language model layer significantly improves agreement with expert judgment while maintaining high recall and low cost.
This study utilizes TIMSS 2023 longitudinal data from nine systems to estimate and standardize the joint probability of students transitioning from below to above both mathematics and science benchmarks, revealing significant system-specific variations and demonstrating that while common-severity standardization clarifies target dependence, the results remain descriptive rather than causal.
This paper argues that European official statistics erroneously attribute the non-use of generative AI to a lack of need because survey design limitations fail to capture critical barriers like disability and cost, thereby mistaking measurement artifacts for genuine public indifference.
This paper demonstrates that PISA's coverage-adjusted top-quarter trends are highly sensitive to the choice of population denominator, revealing significant discrepancies between reported data and World Population Prospects estimates that underscore the need for transparent provenance reporting and caution when synthetic weights trigger adjustments.
This study demonstrates that the measurement precision ceiling inherent in PISA 2022 plausible values fundamentally limits attainable predictive accuracy and destabilizes predictor rankings across domains and education systems, necessitating that performance comparisons and model interpretations be grounded in these computable measurement bounds.
This paper establishes a novel two-stage infection-age epidemic model incorporating nonlocal diffusion, chemotactic avoidance, and waning immunity to prove global stability of equilibria and develop a bilevel optimal control framework with intermittent strategies that, validated by Berlin data, demonstrates the superiority of spatially targeted interventions over uniform approaches.
This paper challenges the conventional preference for Ridge regression in dense-signal high-dimensional settings by demonstrating that Lasso's underperformance stems from suboptimal tuning rather than inherent flaws, and introduces a novel posterior-predictive penalty selector that enables Lasso to achieve predictive accuracy comparable to or exceeding Ridge regression while retaining its crucial variable selection capabilities.
This Monte Carlo simulation study evaluates the performance of BRR, JK2, and Bootstrapping variance estimators in international large-scale assessments, finding that while JK2 offers superior precision for smooth statistics like means, Bootstrapping and BRR are more accurate for non-smooth statistics, and that Fay adjustments and non-response handling significantly influence estimator reliability.
This paper introduces Inverse Target Trial Emulation (ITTE), a Bayesian framework that generates realistic observational datasets from randomized controlled trial data by systematically inducing confounding and time-related biases, thereby enabling the rigorous evaluation and comparison of analytical strategies for adjusting these biases in non-randomized health research.
This metadata analysis of 9,161 retractions reveals that the "computer-generated content" reason in Retraction Watch is heavily concentrated in a single publisher and strongly associated with paper mills, but these patterns reflect co-coding practices rather than providing definitive evidence about the actual presence of generative AI in the retracted articles.