| Dozent/in |
Dr. rer. nat. Hanna Bettine Fechner |
| Veranstaltungsart |
Vorlesung/Übung |
| Code |
FS261253 |
| Semester |
Frühjahrssemester 2026 |
| Durchführender Fachbereich |
Gesundheitswissenschaften |
| Studienstufe |
Bachelor |
| Termin/e |
Mo, 23.02.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 02.03.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 09.03.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 16.03.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 23.03.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 30.03.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 13.04.2026, 10:15 - 12:00 Uhr, HS 3
Mo, 20.04.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 27.04.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 04.05.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 11.05.2026, 10:15 - 12:00 Uhr, 3.B48
Mo, 18.05.2026, 10:15 - 12:00 Uhr, 3.B48 |
| Weitere Daten |
For students enrolled in the B.Sc. in Health Sciences, the course can be
credited in «Vertiefungsbereich Forschungsmethoden». The content of this
course overlaps in part with the Masterseminar “Multilevel Modeling for the
Health Sciences in R” (GMF/Fechner). Students are advised to take only one of
these two courses. For students who wish to major in Health Data Science, the
course “Multilevel Modeling for the Health Sciences in R” is recommended. |
| Umfang |
2 Semesterwochenstunden |
| Inhalt |
For research questions in the health sciences, the context of the data is often of critical importance. This means that the data is grouped or clustered according to specific contexts or levels (e.g., repeated measurements within the same patients or medical devices, measurements on grouped individuals in different hospitals or regions). Linear mixed-effects models (from the family of multilevel models) are statistical methods for analyzing such data and offer a wide range of possible applications in various fields of the health sciences.
After a brief review of regression models with quantitative and qualitative predictors, central principles of linear mixed-effects models are introduced (e.g., data structures with multiple levels, advantages of using linear mixed-effects models, specification of suitable models using fixed and random effects). Linear mixed-effects models for different research designs and data structures are then discussed. Topics include linear mixed-effects models for cross-sectional and longitudinal designs, cross-level interactions, model diagnostics and modifications, and recommendations for the presentation of results.
Each topic is introduced with a brief theoretical overview, followed by practical implementation in R and interpretation of the resulting R output, combined with interactive group work. Students are provided with complementary exercise sheets so that they can gain practical experience with modelling techniques. Students complete the exercises both in class and at home and present their solutions to each other. At the end of the course, students apply their knowledge by developing a research plan for a research question in the health sciences using linear mixed-effects models, thereby placing the modeling techniques covered in context. |
| E-Learning |
Course materials are made available or linked on the e-learning platform Moodle, and solutions to the exercises and research plans are submitted via Moodle |
| Lernziele |
After participating in this methods-oriented course, students will be able to
• describe, explain, and evaluate key fundamentals of linear mixed-effects models
• specify suitable models for data sets that were collected using different research designs and that have different data structures
• implement important steps for data analysis with linear mixed-effects models using R and interpret the results obtained
• develop a research plan for investigating a research question from the health sciences with linear mixed-effects models |
| Voraussetzungen |
Knowledge of statistics/quantitative methods (especially regression analysis) and data visualization.
Experience with the software R and R Studio or the willingness to acquire this knowledge before the start of the course.
Please bring your own laptops with an installation of R and R Studio. |
| Sprache |
Englisch |
| Begrenzung |
The course is limited to 20 participants. The limit is administered
via the voting tool for topic selection in the Moodle course from February 2nd, 2026, 12:00 pm. (noon) onwards . Topics, dates, and
deadlines can be viewed in the Moodle course. As soon as 20 participants are
registered, registration via the voting tool will close. If you would like to be put
on the waiting list, please send an email to: bsc-gmf@unilu.ch. |
| Anmeldung |
Moodle: https://elearning.hsm-unilu.ch/course/view.php?id=976
|
| Leistungsnachweis |
Grading will be based on 1) the coding solutions and presentation of these solutions for an exercise sheet in R (50%), and 2) a research plan in which linear mixed-effects models were used (50%). An overall grade of 4.0 or better is required to successfully complete the course.
IMPORTANT: In order to earn credits and participate at the exam registration via Uni Portal within the exam registration period is MANDATORY. Further information: www.unilu.ch/en/study/courses-exams-regulations/health-sciences-and-medicine/exams/ |
| Abschlussform / Credits |
Coding solutions in R and their presentation, research plan / 3 Credits
|
| Hinweise |
Teaching methods:
Theoretical inputs, demonstrations, exercises, presentations, group work, and discussions by students. |
| Hörer-/innen |
Nein |
| Kontakt |
hanna.fechner@unilu.ch |
| Material |
Course materials are made available or linked on the e-learning platform Moodle, and solutions to the exercises and research plans are submitted via Moodle |
| Literatur |
• Leyland, A. H., & Groenewegen, P. P. (2020). Multilevel modelling for public health and health services research: Health in context. Springer Open. https://doi.org/10.1007/978-3-030-34801-4_1
• Luke, D. A. (2020). Multilevel Modeling (2nd ed.). Sage Publications. https://doi.org/10.4135/9781544310305
• Pinheiro, J., & Bates, D. (2000). Mixed-effects models in S and S-PLUS. Springer. https://doi.org/10.1007/b98882 |