PhD Course: Multi level statistical analyses in social research

Link: The Nordic Centre of Excellence in Welfare: Reassessing the Nordic Welfare Model (REASSESS)

Multilevel modelling has rapidly become established as the appropriate tool for modelling data with complex hierarchical structures. It is important for extending our understanding of social, biological and other sciences beyond that which can be obtained through single level modelling. Multilevel modelling is now being used in Education, Medical science, Demography, Economics, Agriculture and many other areas. The term multilevel refers to a nested membership relation among units in a system. In an education system, for example, students are members of classes, and classes are grouped within schools. When ´single level´ techniques such as multiple regression are applied to data from a structure such as this, the analysis will ignore important aspects of the data structure and the results can be misleading.

The following topics will be covered:

1. Introduction to multilevel models
- Hierarchical data structures
- Variance component models (random intercept)
- Random slope (coefficient) models

2a. Examples of multilevel models
- Simple example (status attainment in local labour markets)
- Further examples
2b. The multilevel model of change

3. Multilevel logistic regression models
- Theory and examples

The course includes lectures and computer exercises. Participants may submit a paper analysing multi level data within three months afterwards as part of their PhD program.

Recommended text:
Hox, Joop (2002): Multilevel Analysis. Techniques and Applications.
London: Lawrence Erlbaum

Morten Blekesaune (NOVA), Kristen Ringdal (NTNU) and Heikki Ervasti (University of Turku) are responsible for the planning of the course.

Registration before 15 April to inger.h.kristiansen@nova.no

For more information contact Morten Blekesaune, NOVA
E-mail: morten.blekesaune@nova.no

Heikki Ervasti, University of Turku
E-mail: heierv@utu.fi