stat papers | Gist.Science

Broadly Applicable Approximate MCMC for Switching Stochastic Differential Equations Using Uniformization and Time-Conditioned Factorized Neural Likelihood Estimation

This paper proposes a broadly applicable approximate Markov chain Monte Carlo sampler for switching stochastic differential equations that combines uniformization with time-conditioned factorized neural likelihood estimation to overcome the limitations of existing methods by enabling Bayesian inference without requiring analytically tractable transition densities.

Shion Hosoda, Michiaki Hamada2026-10-06

📊 statistics

Before Nonresponse: School-Relative Response Timing and Selective Observability in PISA 2025 Context Questionnaires in Latin America

This study of PISA 2025 data from Latin America reveals that late questionnaire nonresponse is often preceded by sustained rapid responding, a transition linked to school-level socioeconomic factors and peer timing, which leads to selective observability that slightly biases regional study-planning estimates but highlights the value of response timing data for distinguishing response quality from missingness.

Jorge Eliécer Villarreal-Fernández2026-10-06

📊 statistics

How Much of the Engagement–Performance Association Survives Adjustment? A Double Machine Learning Study in Online Higher Education

Using double machine learning on a large-scale dataset, this study reveals that while pre-submission online engagement does predict academic performance, nearly half of the raw association is attributable to confounding factors like prior attainment, highlighting the critical need to distinguish predictive signals from causal effects in learning analytics.

Eunseon Jo, Hanjin LEE2026-10-06

📊 statistics

Impact of Lifestyles and Social Attitudes on Happiness Based on CGSS Phase II Modular Data

This study utilizes Bayesian BRPN and FBRPN variable screening within survey-year-adjusted logistic regression models on CGSS Phase II data to identify a comprehensive hierarchy of lifestyle, social attitude, and socio-demographic factors that significantly influence happiness, while also contextualizing the methodological choice through a discussion of the Bayesian–Frequentist debate.

Bojuan Zhao2026-10-06

📊 statistics

Beyond Reported Trips: A Bayesian Framework for Correcting Household Travel Surveys

This study proposes a Bayesian core–satellite framework that integrates GPS-based smartphone survey data with conventional household travel surveys to probabilistically correct recall and proxy-reporting biases, thereby improving the accuracy of trip counts, distances, and attributes for transportation planning.

Melvyn Ming Xi Li, Kaili Wang, Khandker Nurul Habib2026-10-05

📊 statistics

Estimation of Neutrosophic Population Mean Incorporating Auxiliary Information under Simple Random Sampling

This paper proposes and validates an almost unbiased neutrosophic estimator for population mean that incorporates auxiliary information to achieve lower Mean Squared Error and higher efficiency compared to traditional methods when dealing with ambiguous or indeterminate data.

Singh Akansha Ravindrabahadur, Rajesh Singh2026-10-05

📊 statistics

Modelling with κ−deformed quantile functions

This paper establishes a general framework for constructing probability distributions using $\kappa$ -deformed quantile functions, demonstrating how the deformation parameter alters tail behavior and validating the approach's practical utility through parameter estimation and goodness-of-fit analyses on real-world datasets.

N. Unnikrishnan Nair, Silpa Subhash2026-10-05

📊 statistics

Does Machine Learning Improve Depression Prediction Beyond Conventional Clinical Models? A Leakage-Controlled Multicohort Simulation Benchmark

In a leakage-controlled multicohort simulation benchmark, machine learning algorithms failed to consistently outperform appropriately specified logistic regression models for depression prediction, while data leakage produced substantially larger and misleading apparent gains.

Arhama Faridi2026-10-05

📊 statistics

National assignment rate and time to assignment of the Spanish NIE (Número de Identidad de Extranjero) in 2026: a retrospective analysis of 159 certificates with projections for 2027

This retrospective analysis of 159 NIE certificates issued between April and September 2026 estimates a national assignment rate of approximately 940,000 for the year and a median processing time of 10 days, while noting significant limitations regarding data representativeness, funding conflicts, and the absence of ethics approval.

Kay Ventouris2026-10-05

📊 statistics

The Interplay Between Skewness and Sample Size in the Convergence of Sampling Distribution to Normality

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.

Amrit Subedi2026-10-05

← Previous Next →