University of Chicago
- Presentation Slides (PDF)
- List of Unanswered Questions (PDF)
- Data Set Examples (Zipped file containing statistical packages)
If you’re a person with a disability or using assistive technology and are having difficulty accessing any of the content in this file, please contact the ODP at firstname.lastname@example.org.
About the Webinar
Multilevel models are useful for analysis of data in which subjects are nested within some kind of cluster (e.g., students in schools). Such models assume that each subject belongs to only one group. However, students might be nested within primary and secondary schools, where not all students from the same primary school go to the same secondary school. In this case, there is a crossing of the two types of clusters (i.e., primary and secondary schools), and cross-classified multilevel models are necessary for appropriate data analysis. Multiple membership models are for situations in which the subjects are nested within more than one cluster. For example, in a medical scenario, patients may be seen by more than one nurse, and so a patient is a member of multiple clusters (i.e., nurses). Here, the multiple membership multilevel model is needed for analysis. Finally, dynamic multilevel models are used in longitudinal studies in which subjects change cluster membership across time. In this presentation, all three types of extended multilevel models are described and illustrated, with software syntax examples provided.
About Donald Hedeker
Dr. Donald Hedeker is the Professor of Biostatistics in the Department of Public Health Sciences of the University of Chicago. He received his Ph.D. in quantitative psychology from the University of Chicago. His chief expertise is in the development of statistical methods for clustered and longitudinal data, with particular emphasis on mixed-effects models. With Robert Gibbons, Dr. Hedeker is the author of the text “Longitudinal Data Analysis,” published by Wiley in 2006. More recently, he has developed methods and software for analysis of intensive longitudinal data, which are data with many measurements over time, often collected using mobile devices and/or the internet. Such data are increasingly obtained by researchers in many research areas such as mobile health (mHealth) and ecological momentary assessment (EMA) studies.
In 2000, Dr. Hedeker was named a Fellow of the American Statistical Association, and he became an elected member of the International Statistical Institute in 2015. Also in 2015, he received a Long-Term Excellence Award from the Health Policy Section of the American Statistical Association. In 2016, he was elected to the Society of Multivariate Experimental Psychology. Dr. Hedeker has served as an Associate Editor for Statistics in Medicine since 2006.