School of Cultural and Professional Learning and Office of Education Research, Faculty of Education present a two-day workshop to be held on Wednesday, 18th and Thursday, 19th February in B Block, Level 2, Room 240, Kelvin Grove Campus, Victoria Park Road, Queensland University of Technology.
This two-day short course provides an introductory through to intermediate treatment of multilevel modelling for continuous and binary responses (dependent or outcome variables) when the data are clustered or hierarchical. Such methods are appropriate when, for example, analysing the exam scores of students nested within schools, or the health outcomes of patients nested within hospitals. Longitudinal data are also clustered, with repeated measurements on individuals or multiple panel waves per survey respondent.
The format of the course will be lectures only; there will be no hands-on software practical component. However, discussion will be given to the many software options now available for fitting multilevel models. A selection of the following topics will be covered
- Overview of multilevel modelling: multilevel data structures, typical multilevel research questions, problems with standard analyses, ...
- Variance-components models: testing for group effects, variance partition coefficient (VPC) and intraclass correlation (ICC), predicting group effects, shrinkage,
- Random-intercept models: contextual effects, consequence of ignoring clustering,
- Between and within effects of level-1 covariates: fixed- versus random-effects, hybrid-effects, Mundlak formulation, Hausman endogeneity test,...
- Random-coefficient models: cross-level interactions, variance functions (heteroskedasticity),
- Growth-curve models: centring time, polynomial time trends, autocorrelated residual errors, complex level-1 variability, ...
- Three-level models: consequences of ignoring clustering at different levels, ...
- Cross-classified models: interaction classifications, consequences of ignoring cross-classified structure, ...
- Multiple membership models: alternative weighting schemes, consequences of ignoring multiple membership structure, ...
- Binary response models I: odds, odds ratios, probabilities; latent response formulation,
- Binary response models II; population-averaged (marginal) vs. cluster-specific (conditional) inference, ...
- Multilevel modelling resources: useful web sites, online course, software, discussion boards, email lists, books, ...
Each new methodological development will be illustrated with applications to social science data sets.
Dr George Leckie, a visiting fellow at Queensland University of Technology, is a Senior Lecturer in Social Statistics at the Centre for Multilevel Modelling and Graduate School of Education at the University of Bristol. He also holds a status-only Associate Professor position at the Graduate Department of Applied Psychology and Human Development, University of Toronto, Canada. His methodological interests are in the application and dissemination of multilevel and other latent variable models to analyse educational and social science data. His substantive interests include: school performance indicators and their associated publication in league tables; value-added models (VAMs) for measuring school and teacher effects on student achievement; and modelling rater effects on test scoring. He currently holds an ESRC Future Research Leaders grant and has previously been a co-investigator on several other ESRC grants. His research has been published in various international journals, including: Journal of the Royal Statistical Society, Series A; Journal of Educational and Behavioral Statistics; Journal of Educational Measurement; and Journal of Statistical Software. He has taught multilevel modelling short courses across Europe, Australia and US. http://www.bristol.ac.uk/cmm/team/leckie.html
Participants should be familiar with estimating and interpreting linear and logistic regression models, including the writing and interpretation of model equations, hypothesis testing and model selection, and the use and interpretation of dummy variables and interaction terms. Some participants may wish to refresh themselves of this material by reading modules 3 and 6 of the LEMMA online course. http://www.bristol.ac.uk/cmm/learning/course-topics.html
Optional background reading
Duncan et al. (1998) provide a non-technical introduction (no equations) to multilevel modelling. Chapter 2 of Hox (2011) provides a more technical introduction.
Duncan, C., Jones, K., & Moon, G. (1998). Context, composition and heterogeneity: using multilevel models in health research. Social science & medicine, 46, 97-117.
Hox, J. (2011). Multilevel analysis: Techniques and applications, 2nd edition. Lawrence Erlbaum Associates: Mahwah, NJ.
Please RSVP through Doorway to Research - Event 216 to claim your spot!
- 18 February 2015 - 19 February 2015
- Kelvin Grove Campus, Victoria Park Road, Queensland University of Technology
- Room 240, B Block, Level 2
- School of Cultural and Professional Learning and Office of Education Research, Faculty of Education
- RSVP through Doorway to Research - Event 216 to claim your spot!
- Calendar Event
- Add Event to Calendar
Dr George Leckie