Oxford BRC Stats Hub Lunchtime Seminar Series: Multilevel modelling in clinical trials
Daphne Kounali
Wednesday, 09 April 2025, 1pm to 1.30pm
Hosted by octru-stats@ndorms.ox.ac.uk
This is the eighth (and final) in a series of lunchtime seminars organised by the Oxford BRC Statistics Hub. Each seminar is 20 minutes long followed by 10 minutes of Q&A, and will be held via Microsoft Teams. These seminars are open to all in the University of Oxford and Oxford University Hospitals NHS Trust.
Multilevel modelling in clinical trials
Daphne Kounali - OCTRU Lead Statistician
A multilevel model is a statistical tool used to analyze data with a complex dependence structure, such as when patients are nested within hospitals or when there are multiple levels of treatment providers and geographic locations. In this seminar, I will define the different types of structures in clinical trials and discuss various applications of multilevel models, including incorporating repeated measurements, accounting for drop-out, and addressing measurement error. I will demonstrate how realistic assumptions and focusing on structure can help understand contextual effects and heterogeneity in outcomes, providing more precise estimates of treatment effects and predictions.
No registration is required.
Click here to join the session.