ASTK18010U Core subject: Advanced Quantitative Methods in the Study of Political Behavior

Volume 2020/2021
Education

Core subject in the core-subject line in Political Behavior. Only accessible to students who are admitted to the core-subject line.

NB! All exams (both ordinary and re-exams) will take place at the end of the autumn semester only, as the course is not offered in the spring

Content

This seminar is part of the specialization in Political Behavior and Applied Quantitative Methods. It covers the applied approaches to quantitative methods that are commonly used in the study of political behavior. The course is designed to interact closely with Political Behavior—the specialization's substantive course—and incorporates its texts and themes. We will examine some of the seminal literature on political behavior and ask: How have the authors arrived at their results? Can we reproduce them? And how sensitive are they methodological choices? The course places particular emphasis on students' ability to independently apply the methods introduced in the course to real-world data.

 

The course revolves around three themes. The first, Brush-up (classes 1-4), re-introduces central aspects of Methods 2, up to and including regression analysis, and introduces the R statistical programming language.

 

For the second theme, Causal Inference (classes 5-11), we will introduce a paradigm for how to think about causality, and examine the primary methods for estimating causal effects with experimental and observational data. This theme arises from the fact that the social sciences have recently undergone a "credibility revolution" that places methods for the estimation of causal effects center-stage. In this tradition, the course will introduce research designs and statistical techniques for causal inference. Particular emphasis is placed on research design, because well-crafted designs can often eliminate the need for more advanced statistical methods that can rely on implausible assumptions.

 

For the third theme, Data Science (classes 12-14), we will introduce techniques for collecting and analyzing data from non-traditional sources, such as those from unstructured online data (e.g. text).

 

Tentative schedule

 

1. R Basics I

2. R Basics II

3. OLS

4. R Advanced & Data Visualization

5. Introduction to Causal Inference

6. Experiments I

7. Experiments II

8. Instrumental Variables

9. Panel Data

10. Difference in Differences

11. Regression Discontinuity Designs

12. Web-scraping

13. Text as data

14. Social Data Science

Learning Outcome

Knowledge:

Identify relevant designs and techniques for answering research questions in political behavior.

 

Skills:

Process data in structured and unstructured formats for subsequent analysis.

 

Competences:

Analyze empirical questions in political behavior using quantitative data.

Books

  • GG: Gerber, A. S., & Green, D. P. (2012). Field experiments: Design, analysis, and interpretation. WW Norton.
  • AP: Angrist, J. D., & Pischke, J. S. (2014). Mastering ’metrics: The path from cause to effect. Princeton University Press.

 

Articles

  • Benoit, K., & Nulty, P. (2016) Getting Started with quanteda
  • Grimmer, J., & Stewart, B. M. (2013). Text as data: The promise and pitfalls of automatic content analysis methods for political texts. Political Analysis, 21(3), 267-297.
  • Hariri, J. G. (2012). Kausal inferens i statskundskaben. Politica, 44(2), 184-201.
  • Justesen, M. K., & Klemmensen, R. (2014). Sammenligning af sammenlignelige observationer. Politica, 46(1), 60-78.
  • Leeper, T. (2016). Really Introductory Introduction to R.
  • Montgomery, J. M., & Olivella, S. (2017). Tree-based models for political science data. American Journal of Political Science, forthcoming.
  • Samii, C. (2016). Causal empiricism in quantitative research. Journal of Politics 78(3): 941–955.
  • Varian, H. R. (2014). Big data: New tricks for econometrics. The Journal of Economic Perspectives, 28(2), 3-27.
  • Wickham, H. (2014). Tidy data. Journal of Statistical Software, 59(10), 1-23.
  • Zhang, C. (2017). Tricks for cleaning your data in R.

 

Cases

  • Angrist, J. D., & Pischke, J. S. (2010). The credibility revolution in empirical economics: How better research design is taking the con out of econometrics. Journal of Economic Perspectives, 24(2), 3-30.
  • Baturo, A., & Mikhaylov, S. (2013). Life of Brian revisited: Assessing informational and non-informational leadership tools. Political Science Research and Methods, 1(01), 139-157.
  • Carroll, Aaron E. (2018). Workplace Wellness Programs Don’t Work Well. Why Some Studies Show Otherwise. The New York Times, August 6, 2018.
Passed Methodology 2/3, DAK2, and DAK3 or equivalent
A mix of class lecture, labs, and home exercies
  • Category
  • Hours
  • Class Instruction
  • 28
  • Total
  • 28
Continuous feedback during the course of the semester

Students receive feedback on both portfolio assignments

Credit
7,5 ECTS
Type of assessment
Portfolio
Portfolio exam
Marking scale
7-point grading scale
Censorship form
No external censorship
Re-exam

Free written assignment

Criteria for exam assesment
  • Grade 12 is given for an outstanding performance: the student lives up to the course's goal description in an independent and convincing manner with no or few and minor shortcomings
  • Grade 7 is given for a good performance: the student is confidently able to live up to the goal description, albeit with several shortcomings
  • Grade 02 is given for an adequate performance: the minimum acceptable performance in which the student is only able to live up to the goal description in an insecure and incomplete manner