Confidence Without Competence? Exploring Gender Gaps in Mathematics Self-Efficacy and Academic Success in Engineering.

This repository provides the supplementary research materials associated with the article “Confidence Without Competence? Exploring Gender Gaps in Mathematics Self-Efficacy and Academic Success in Engineering.” In the journal "Cogent Education". The study examined the relationships among diagnostic mathematics performance, mathematics self-efficacy, gender, and first-semester academic outcomes in a cohort of first-year engineering students in Mexico. The repository includes the following materials: Synthetic dataset (syn_data.csv): a privacy-preserving synthetic version of the study database, generated from the original dataset to enable transparent inspection of the analytical structure without exposing participant-level confidential information. Statistical analysis code: R scripts documenting the analytical procedures used in the article, including descriptive analyses, correlation matrices, group comparisons, MANOVA/MANCOVA models, and regression analyses. Synthetic data generation code: R script used to generate the synthetic dataset from the original database. The original dataset contained 777 participant records and variables related to gender, engineering major, differential calculus performance, first-semester grades, mathematics self-efficacy scores, and diagnostic mathematics test results. Because the original database is subject to confidentiality restrictions, it is not made openly available. The synthetic dataset and code are shared to promote transparency, reproducibility, and secondary methodological learning. Propuesta de nota para el artículo Si quieres dejar constancia dentro del paper, esta formulación funciona bien: Data availability statement:The original dataset used in this study is not publicly available due to participant confidentiality considerations. However, the synthetic dataset and the R scripts used for data analysis and synthetic data generation are openly available in Zenodo at: [DOI to be inserted after deposit]. Y si quieres una versión más fuerte en ciencia abierta: Data and code availability statement:To support transparency and reproducibility while protecting participant confidentiality, the original raw dataset is not publicly shared. A synthetic dataset reproducing the structure of the study data, together with the R scripts used for statistical analysis and synthetic data generation, is available in Zenodo at: [DOI to be inserted after deposit]. Recomendación final Mi recomendación académica es esta: sí conviene retirar los anexos del manuscrito, pero no perder los materiales; más bien, conviene formalizarlos mejor en Zenodo con un DOI y sustituir los anexos por una declaración breve de disponibilidad de datos y código. El punto más delicado es decidir si el archivo Data Base Manuscript.csv debe o no hacerse público. Dado que tu manuscrito declara restricciones de confidencialidad, yo no lo publicaría abiertamente salvo que estés completamente seguro de que no existe riesgo de reidentificación. En cambio, sí publicaría con confianza: syn_data.csv el código de análisis el código de generación de datos sintéticos y un README bien redactado.