Hauptseminar: Experiments on Voting
Course Details
Course Instructor: Nan Zhang (Office hours by appointment)
Course Website: https://nanzhang-polisci.github.io/Turnout_FSS26
Date and Time: Wednesday, 10:15-11:45 in B244 Hörsaal (A5, 6)
Course Description
Political participation represents an enduring puzzle for political scientists: given that an individual vote is rarely decisive, why do people bother to go to the polls? In this seminar, we will address this question via some of the latest experimental research on voting and turnout. The goal is provide students with both an overview of recent evidence on voting behavior, as well as an applied introduction to state-of-the-art methods for drawing inferences from experimental and observational data.
Course Structure and Requirements
This course will follow a “flipped classroom” model:
- students are expected to complete an assigned reading before each class meeting
- each meeting will begin with a short quiz on the main ideas from the assigned readings
- we will then spend the remainder of class time discussing the quiz / readings
Diligent preparation and active participation are essential for the success of this class! In addition to the theories and main findings in each article, we will also spend considerable time discussing the article’s methods as well as how the researchers arrive at their (causal) conclusions.
This way of approaching the material is hard, especially if you are encountering it for the first time, so don’t be afraid to ask questions! This is how you will learn.
To encourage participation from everyone, I may randomly select several students to speak during each class session. The idea is not to cause anyone stress or anxiety, but rather to “break the ice” and foster a more “active” and collaborative environment where everyone can feel comfortable to participate.
If you are worried about this “cold calling” policy, please come see me.
Since participation is central to what we do in class, I will be keeping a record of attendance. You are allowed two unexcused absences during the semester. Any additional absences should be approved by me beforehand.
Assessment
Your final grade will be based a Hausarbeit (final paper).
This essentially consists of a very long quiz (similar to what we do every week) that asks you to apply the ideas we covered in the semester to different scenarios.
Instructions will be handed out on TBA, and you should submit your assignment via email by 23:59 on TBA.
Weekly Schedule
Note: the current version of the syllabus is a work in progress. In fact, it’s probably too much to cover in one semester. I will make adjustments, depending on the pace of the class, so check back often!
All changes to the syllabus will be announced in class.
Week 1 (11 Feb): Course Introduction
Nan will introduce the course, go over the syllabus, and answer any logistical questions you may have.
We will then discuss the difference between descriptive vs. causal research questions, and begin to think seriously about the problem of self-selection in studies of political participation.
Reading for next week:
NOTE: the article uses a probit model, which is basically doing the same thing as logistic regression. If you need a reminder about how logistic regression works, check out this playlist.
Week 2 (18 Feb): Potential Outcomes and Randomization
We will discuss the potential outcomes framework for drawing causal inferences from data, as well as the essential role of randomization.
Reading for next week:
- Atkinson and Fowler. Social Capital and Voter Turnout: Evidence from Saint’s Day Fiestas in Mexico
Week 3 (25 Feb): As-If Random
How can we apply to logic of experiments to other situations where the treatment is “as good as random”?
Reading for next week:
Week 4 (4 March): Uncertainty
We will talk about statistical uncertainty, standard errors, and hypothesis testing via randomization inference.
Reading for next week:
- Gerber and Green. The Effects of Canvassing, Telephone Calls, and Direct Mail on Voter Turnout: A Field Experiment
Week 5 (11 March): Instrumental Variables
We will discuss the problem of experimental non-compliance and how to address this issue using instrumental variables.
Reading for next week:
- White. Misdemeanor Disenfranchisement? The Demobilizing Effects of Brief Jail Spells on Potential Voters
Week 6 (18 March): Instrumental Variables (cont’d)
We will continue talking about IV, 2SLS and continuous treatments and instruments.
We will also take some time at the end of class for a midterm check-in on how the semester is going so far.
Reading for next time (after Easter):
NO CLASS: 25 March
Easter Break: 31 March and 7 April
Week 7 (15 April): Regression Discontinuity
We will discuss the basics of regression discontinuity designs.
Reading for next week:
- Hainmueller et al. Naturalization fosters the long-term political integration of immigrants
Week 8 (22 April): Regression Discontinuity (cont’d)
We will discuss “fuzzy” RDD - a combination of RDD and IV!
Reading for next week:
- Eckholm et al. More a Swell than a Ripple: The Persistent Impact of the 2004 Boxing Day Tsunami on Voter Turnout
Week 9 (29 April): Matching
We will discuss some basic ideas behind matching.
Reading for next week:
Week 10 (6 May): Difference-in-differences.
We will discuss the basic idea behind difference-in-differences.
Reading for next week:
- Ben-Menachem and Morris. Ticketing and Turnout: The Participatory Consequences of Low-Level Police Contact
Week 11 (13 May): DiD and Matching.
Our example today will demonstrate how matching can be used to strengthen the credibility of the parallel trends assumption in DiD.
Reading for next week:
Week 12 (20 May): Mixed-Methods Research
We will discuss how qualitative evidence can be used to improve the interpretation of causal designs.
Assignment for next week:
- Please bring your own questions to class next week. I will not prepare any materials in advance!
Week 13 (27 May): Review and Discussion of Final Exam
References
If you are looking for more materials on causal inference, you can check out Andrew Heiss’ Program Evaluation class, or this excellent ebook by Nick Huntington-Klein: theeffectbook.net.
Both resources are free, provide code examples, and are accompanied by youtube videos!
Finally, StatQuest by Josh Starmer has an excellent set of youtube videos reviewing basic statistical concepts and linear regression.