Short Bio
Zoltán Fazekas is a Post-Doctoral Researcher in Political Behavior and Individual Differences at the Department of Political Science and Public Management, University of Southern Denmark. He earned his PhD in political science at the Department of Methods in the Social Sciences, University of Vienna where he was an Early Stage Researcher in the Marie Curie Initial Training Network in Electoral Democracy (ELECDEM). He holds a BA in Economics, MA in European Affairs and an MA in Political Science. His fields of interest are: comparative electoral behavior, political psychology, and quantitative methods. He prefers simultaneous estimation and truly dislikes the quest for R2 maximization. You can find more information about his research and publications at: http://zfazekas.github.io.
Prerequisite knowledge
Note from the Academic Convenors to prospective participants: by registering to this course, you certify that you possess the prerequisite knowledge that is requested to be able to follow this course. The instructor will not teach again these prerequisite items. If you doubt whether you possess that knowledge to a sufficient extent, we suggest you contact the instructor before you proceed to your registration.
Students should be able to comfortably use R (or transition fast from STATA/SPSS, which is easy) and have a solid prior knowledge of linear regression, including a solid understanding of assumptions. We will do a brief review of linear regression, but that does not substitute in depth knowledge and experience with linear regression models (OLS and maximum likelihood). Three sample books that can help in reviewing these concepts are:
1. Achen, C. H. (1982). Interpreting and using regression (Vol. 29). Sage Publications, Incorporated.
2. Lewis-Beck, M. (1980). Applied regression: An introduction (Vol. 22). Sage Publications, Incorporated.
3. Eliason, S. R. (1993). Maximum likelihood estimation: Logic and practice (Vol. 96). Sage Publications, Incorporated.
For R, students can consult many freely available resources, but a good book to accompany a systematic review is: Adler, J. (2010). R in a Nutshell: A Desktop Quick Reference. O'Reilly Media
Short course outline
The present course is aimed at familiarizing students with principles of multilevel modelling and its implementation in R. The course manual is Gelman and Hill (2007) and the two main R packages used will be lme4 and nlme. Broadly speaking, we will build and estimate models that step-by-step get more complex, discussing each decision in this process. Although this is a methods course, each and every lecture will focus on how the statistical model is linked to possible theories or particular hypotheses with added focus on potential limitations and correct interpretation. After laying the basic foundations, during the second week we switch gears and work with more complex models (i.e. deep interactions, cross-classified models, longitudinal analysis). By the end of the course, participants are expected to be able to clearly argue why they use in their own research papers a multilevel model, which specification suits the research question and the data (including relatively complex questions and data structures), how the models are specified, what the results mean and how they can be integrated with previous research. Each lecture will discuss both theoretical principles and practical implementations, whereas the lab sessions are designated solely to issues related to practical implementation.
