Multiple Regression Analysis and Fundamentals of Causal Inference
This course will provide students with a comprehensive understanding of the theory and practice of multiple regression analysis, including how to interpret regression coefficients and how to use regression analysis to test hypotheses and make predictions. In addition to learning multiple regression analysis, students in this course will also gain an understanding of the fundamental principles of causal inference. This includes distinguishing between correlation and causation, recognizing the impact of confounding variables, and learning techniques to establish causality. Students will also come to appreciate the critical role that multiple regression plays as a fundamental statistical tool in causal inference. The focus on multiple regression and causal inference entails a strong focus on different research designs, including randomized controlled trials, quasi-experimental designs, and observational studies, and how to choose the appropriate design for a given research question. To gain hands-on experience, students will learn how to use R to conduct multiple regression analysis and causal inference techniques. Thereby the students will explore how multiple regression analysis and causal inference can be applied to sociological research questions, such as the effects of social class on educational attainment or the impact of discrimination on health outcomes. Overall, this course will provide students with a strong foundation in statistical analysis and causal inference, which are essential skills for conducting sociological research.
The schedule can be found here
Compulsery course on the 3rd semester BSc in Sociology.
(Former: Advanced Quantitative Methods)
Credit and exchange students must be at bachelor level.
The course introduces students to multiple regression analysis, the fundamentals of causal inference, and their application to sociological research questions. Thereby, students gain knowledge of:
- Multiple linear regression and all their important parameters,
- Statistical hypothesis tests and their use in multiple regression analysis,
- Assumptions of multiple OLs regression,
- Randomized controlled trials,
- Instrument variable regression,
- Interaction effects,
- Regression discontinuity designs.
The course gives students the opportunity for practical mastery of regression analysis in R. Accordingly, upon completion of the course students will be able to:
- Conduct multiple regression analysis in R,
- Correctly interpret regression coefficients,
- Use statistical hypothesis tests to answer sociological questions,
- Select relevant control variables for a multiple regression analysis,
- Specify and correctly interpret interaction effects,
- Specify and correctly interpret polynomials to specify non-linear relationships,
- Conduct instrument variable regression in R,
- Conduct regression discontinuity designs in R,
- Compare model fit,
- Conduct model checks,
- Visualize and communicate multiple regression results,
- Critically evaluate the results of multiple regression analysis.
After completing this course, students will be able to:
- Evaluate the effects of policies, organizational innovations, and so on.
- Identify different causal factors explaining a phenomena,
- Distinguish mere correlations from actual causal relationships,
- Use knowledge and skills for research and consulting,
- Analyze various types of data and quickly gain a working understanding of new data sources,
- Write reports that involve advanced statistical data analysis,
- Acquire further advanced quantitative methods training in factor analysis, multilevel modelling, panel data analysis, or computational sociology.
The three-hour weekly lecture contains two conventional lectures of 45 minutes, and two 20 minutes exercises where students solve tasks using R. In addition to the weekly lecture, there are also weekly tutorials taught by student instructors where lecture materials and exercises are reviewed in smaller groups. On top of that there are weekly online quizzes on Absalon that give automated feedback.
De Veaux, Richard, Paul F. Velleman, and David E. Bock. 2021. Stats. Data and Models. Boston: Pearson & Addison Wesley.
Angrist, Joshua D., and Jörn-Steffen Pischke. 2014. Mastering ‘Metrics: The Path from Cause to Effect. Princeton University Press.
Students should have a completed “Intro til R” and “Basic Statistics”, or other courses that cover the same content.
Requirement: Own laptop with running and updated versions of RStudio and R.
Weekly mandatory online quizzes will give students automated feedback on single tasks. Moreover, students will get further feedback in weekly tutorials given by student instructors. The latter will also be helping with feedback throughout the exam period up until submission of their final integrated exam.
- Full-degree students – sign up at Selfservice on KUnet
- Exchange and guest students from abroad – sign up through Mobility Online and Selfservice
- Credit students from Danish universities - sign up through this website.
- Open University students - sign up through this website.
- 7,5 ECTS
- Type of assessment
- Type of assessment details
- To get qualified for the integrated written take-home exam, the
students should hand in at least 10 of the weekly Absalon online
quizzess. The quizzes need to be handed in within two weeks after
they are made available online. Note that the quizzes are not
graded and thus there is also no pass-threshold. Students simply
need to complete 10 quizzes.
The written take-home assignment is integrated with the exam in “Velfærd, ulighed og mobilitet” and based on a set of questions that need to be answered individually or in a group of max four students. The scope of the written take-home essay is a maximum of 10 pages. For group assignments, an extra 5 pages are added per additional student.
- Marking scale
- 7-point grading scale
- Censorship form
- No external censorship
Criteria for exam assessment
Please see the learning outcome.
- Exam Preparation
- Course number
- 7,5 ECTS
- Programme level
- Vejl. 110
- Department of Sociology, Study Council
- Department of Sociology
- Faculty of Social Sciences
- Merlin Schaeffer (4-7169776744777367326f7932686f)
- 23E-;Hold1;;Multiple Regression Analysis and Fundamentals of Causal Inference
- 23E-;Hold2;;Multiple Regression Analysis and Fundamentals of Causal Inference
- 23E-;Hold3;;Multiple Regression Analysis and Fundamentals of Causal Inference
- 23E-;Hold4;;Multiple Regression Analysis and Fundamentals of Causal Inference
Are you BA- or KA-student?
Courseinformation of students