Course Objective
In this course, Research Master students will learn how to apply statistical methods that can be used to test causal effects with quantitative observational data. The course focuses on the application of regression-based techniques (i.e., linear and logistic regression as well as their extensions for nested and longitudinal data).After completing the course, students should be able to:
• understand and apply different statistical methods to examine cause-effect relationships based on quantitative observational data;
• handle cross-sectional, nested and longitudinal data in the statistical software R;
• choose and justify the appropriate statistical model to address a correlational or causal research question;
• interpret the results of the analyses produced in R addressing this question;
• present and visualize their research results in a final assignment that resembles the results section of a journal article
Course Content
n the first part of the course, students are reminded of/introduced to two workhorses of regression-based statistics: ordinary least squares and logistic regression models that can be used in the analysis of cross- sectional and non-nested data. In the second part of the course, students learn statistical models that can be applied to nested and longitudinal data: multilevel models, panel regression techniques and event-history models. Students will use the software R to estimate statistical models.Teaching Methods
Each course week consists of a lecture and a computer lab session. While the lectures focus on developing a basic understanding of advanced multivariate modelling as well as discussing the related advantages and disadvantages, the lab’s purpose is to offer students first-hand experience with conducting and interpreting regression-based analyses using R. During the lecture and the tutorial several datasets will be used for the purpose of testing the statistical models. Sometimes, lecturers will make formative assignments available to students via Canvas or TestVision. Students are strongly advised to make these assignments as they will assist them to master the material of the course.Method of Assessment
Students’ grade will be based on the following forms of assessment:• Presentation of findings (20% of the final grade).
• Final research paper (80% of the final grade).
Literature
Agresti, A. (2018) An Introduction to Categorical Data Analysis, 3rd Edition, John Wiley & Sons, Inc, Hoboken, New Jersey.Allison, P.D. (2014), Event History and Survival Analysis, Beverly Hills, CA: Sage.
Darlington, R. and Hayes, A. (2017) Regression Analysis and Linear Models Applications, and Implementation, The Guilford Press, London.
Hox, J. J., Moerbeek, M., & van de Schoot, R. (2017). Multilevel Analysis: Techniques and Applications (Third). Routledge.
Grimm, K. J., Ram, N., & Estabrook, R. (2016). Growth Modeling: Structural Equation and Multilevel Modeling Approaches.
Target Audience
Research Master in Social Sciences, University of AmsterdamAdditional Information
Course is given at the University of AmsterdamRecommended background knowledge
Basic knowledge of descriptive and inferential statisticsLanguage of Tuition
- English
Study type
- Master