The purpose of Multilevel models, also known as mixed models are used to analyse correlated observations. Correlated observations can occur, for instance, when subjects are clustered within neighbourhoods, patients are clustered within hospitals, students are clustered within schools, etc. Besides this, correlated observations also occur in longitudinal studies where the repeated measurements over time are clustered within each individual. Multilevel analysis provides a very elegant and powerful tool to deal with this clustering, i.e. to deal with correlated observations. For longitudinal data analysis, besides multilevel analysis, also other methods, such as GLM for repeated measures and generalised estimating equation (GEE) analysis, are available.
The course is given on location, but it is also possible to take the course online.
If you choose to follow the course on location, you will follow the lectures and the practicals in Amsterdam. If you choose the online variant, you follow all the lectures and practicals via Zoom at the place that suits you best.
When you register for the course, you can indicate which variant you choose. It is not possible to switch between these two options during the course.
This six-day course will explain the basic concepts of multilevel analysis, some specific application of multilevel analysis and will further focus on longitudinal data analysis. The latter includes standard modelling, alternative modelling and the analysis of RCT data. It is an applied course, so the emphasis lies on the interpretation of the results from the different analyses and not on the mathematical background. Lectures are given in the morning and in the afternoon a computer practical is given using the statistical programs STATA, SPSS and R.
If a course is [Full], you can still register, but you will be placed on a waiting list. We will contact you as soon as a place becomes available. At that time you can still decide whether you want to participate in the course.
Multilevel models, also known as mixed models are used to analyse correlated observations. Correlated observations can occur, for instance, when subjects are clustered within neighbourhoods, patients are clustered within hospitals, students are clustered within schools, etc. Besides this, correlated observations also occur in longitudinal studies where the repeated measurements over time are clustered within each individual. Multilevel analysis provides a very elegant and powerful tool to deal with this clustering, i.e. to deal with correlated observations. For longitudinal data analysis, besides multilevel analysis, also other methods, such as GLM for repeated measures and generalised estimating equation (GEE) analysis, are available.
The course is designed for researchers who work with mixed model analysis or researchers who plan to work with mixed model analysis. It is an applied course, so the mathematics behind the mixed model analysis is not discussed in detail.
This course requires that you have completed the course Regressietechnieken (V30) of EpidM or you have acquired comparable knowledge in some other way. If you have not followed the course Regressietechnieken (V30), please state on the application form in the comments box what prior knowledge you have and how you obtained it. The course coordinator will then decide whether you can be admitted to the course.
The course materials (lectures, assignments, feedback of the assignments etc) are available on Canvas, our digital learning environment. The documents will remain available on Canvas for at least one year.
To be able to do the computer practicals of this course you will need:
1. STATA; if you do not have STATA on your laptop, you may be able to arrange STATA through your employer. STATA can be made available via VIEW for employees of the Amsterdam UMC location VUmc. Employees of the Amsterdam UMC location AMC can apply for STATA at AMC’s ICT. If you work at Radboud University Nijmegen, you can purchase STATA via Surfspot.
Unfortunately no trial versions are available for STATA.
and
2. SPSS; if you don’t have SPSS on your laptop, you can purchase SPSS through Surfspot at a very reasonable price. If you do not want to purchase SPSS, you can use the trial version that IBM makes available. See SPSS Software | IBM
Please note:
1. If it is impossible to obtain STATA, it is also possible to do all practicals with SPSS.2. STATA and/or SPSS are the standard software to be used for the computer practical. However, if you are an experienced R user, it is also possible to work independently on the assignments with R. Answer keys are available, but the practical is not supported in terms of guidance in R.
Twisk JWR. Applied mixed model analysis. A practical guide. Cambridge University Press, 2019ISBN: 978-1-108-48507-4 (hardback)ISBN: 978-1-108-72776-1 (Paperback).
Twisk JWR. Applied Longitudinal Data Analysis for Epidemiology. 2nd Revised edition, Cambridge University Press, 2013. ISBN 9781107699922
Students participating in the course as part of the Master’s programme Epidemiology need to pass the exam in order to complete the course.
Students not participating in Master’s programme Epidemiology who sign up for this course as a separate / single course can optionally register for the exam. The examination fee is € 160 per registration.
You can register for the exam via the website: Exams. Registration will close 3 weeks prior to the exam.
Please note that you need to pass the exam in order to receive credits (EC).
A certificate of participation will be granted to all students who have attended at least 80% of the classes. Only contact hours are stated on this certificate.
Only for Dutch medical specialists!
If you wish to be considered for accreditation points by the KNMG , you must sign the attendance list on the last day of the course.
To qualify for the accreditation points, you must have been present the whole course.
Programme Director EpidM, Professor in Applied biostatistics in longitudinal research, Amsterdam UMC