RT info:eu-repo/semantics/article T1 Disentangling doctoral well-being support in progress-focused workshops: Combining qualitative and quantitative data in single-case learning analytics A1 Dimitriadis, Yannis A1 Prieto Santos, Luis Pablo A1 Jovanovic, Jelena A1 Odriozola González, Paula A1 Rodríguez Triana, María Jesús A1 Díaz Chavarría, Henry Benjamín A1 Dimitriadis, Yannis K1 Doctoral education K1 Learning analytics K1 Well-being K1 Idiographic methods K1 Mixed methods K1 58 Pedagogía AB Doctoral education (DE) suffers from widespread well-being issues. Recent evidence from short-term trainingactions shows potential to address them, but also large variability. Further, DE practitioners face challenges inunderstanding whether (and for whom) such interventions work, due to small sample sizes, short interventiondurations, and the inherent uniqueness of each dissertation. This methodological paper proposes a novel,practice-oriented, and idiographic approach to such understanding, supported by learning analytics of quanti-tative and qualitative data. To illustrate this approach, we apply it to two datasets from six authentic doctoralworkshops (N = 105 doctoral students), showcasing how it can provide individualized practice-oriented insightsto doctoral students and help trainers better understand their interventions, while coping with typical limitationsof data from doctoral training. These findings exemplify how the triangulation of simple, interpretable analyticsmodels of mixed longitudinal data can improve students, practitioners’, and researchers’ understanding, re-design, and personalization of such training actions.Educational relevance and implications statement: Collecting data about the context and process of a doctoraltraining action can help practitioners and students understand who benefits more (or less) from such training.The individualized analysis of such data, obtained with even very simple technologies, can also help studentsunderstand their processes and contexts, to better address progress and well-being issues. The use of student-authored short narratives (e.g., diaries), along with longitudinal quantitative data, plays an important role inthese personalized analyses, and the promise of automated qualitative coding makes this approach increasinglyfeasible PB Elsevier SN 1041-6080 YR 2025 FD 2025 LK https://uvadoc.uva.es/handle/10324/76150 UL https://uvadoc.uva.es/handle/10324/76150 LA eng NO Learning and Individual Differences, 2025, vol. 121, p. 102705 NO Producción Científica DS UVaDOC RD 05-jul-2025