Reproducibility Package for "From Statistical Significance to Practical Relevance: A Monte Carlo Comparison of NHST, TOST, Second-Generation p-Values, REACT, and Bayesian HDI-ROPE"

This reproducibility package accompanies the study “From Statistical Significance to Practical Relevance: A Monte Carlo Comparison of NHST, TOST, Second-Generation p-Values, REACT, and Bayesian HDI-ROPE.”The package contains the canonical R implementation, simulation-design files, deterministic rand...

Descripción completa

Guardado en:
Autores principales: Evergisto Sare Lara, Juan Francisco Agreda Vega, L. Montoya, Jimmy Aurelio Rosales-Huamaní
Formato: Software
Lenguaje:inglés
Publicado: 2026
Materias:
null hypothesis significance testing
two one-sided tests
React
practical relevance
statistical power
operating characteristics
heavy-tailed distributions
skewed distributions
Monte Carlo simulation
Statistical Methods and Bayesian Inference
Statistical Methods in Clinical Trials
Meta-analysis and systematic reviews
Acceso en línea:Enlace permanente (DOI o Handle)
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Sumario:This reproducibility package accompanies the study “From Statistical Significance to Practical Relevance: A Monte Carlo Comparison of NHST, TOST, Second-Generation p-Values, REACT, and Bayesian HDI-ROPE.”The package contains the canonical R implementation, simulation-design files, deterministic random seeds, validated aggregate simulation outputs, quality-control reports, publication table and figure source data, manuscript-facing assets, and R session information.The study compares five inferential procedures: null-hypothesis significance testing (NHST), two one-sided tests (TOST), second-generation p-values (SGPV), REACT, and Bayesian HDI-ROPE. The reference Monte Carlo design considers six sample sizes, three practical-relevance thresholds, 29 true mean differences, and 20,000 replications per data-generating scenario, together with sensitivity analyses under heteroscedastic normal, heavy-tailed, and skewed distributions.Raw scenario-level checkpoint files are not included in this compact deposit because they can be deterministically regenerated from the supplied code and random seeds. The aggregate outputs required to reproduce and verify the reported tables, figures, operating characteristics, sensitivity analyses, and quality-control results are included.

Ejemplares similares