POLS 7012: Introduction to Political Methodology
Welcome to our course website! Here you can find links to everything you’ll need this semester:
The course syllabus (this page or in PDF)
Submit assignments at our course eLC page (mortarboard icon in the upper right).
I will post code and data on the course GitHub repository (the octocat icon in the upper right).
Syllabus
This course will introduce the foundational mathematical and computational skills you will need to conduct and evaluate political science research. During the first half of the semester, we explore the methods that political scientists use to grapple with several fundamental problems in empirical work: causal inference, measurement, sampling, and prediction. In the second half, we learn essential concepts from probability theory that researchers use to help distinguish patterns from noise in data. Throughout, we will focus on building the practical computational skills you need as a practicing political scientist. By the end of the semester, you will be armed with the necessary tools to tackle the more advanced material that makes up the rest of our graduate methods sequence.
Course Objectives
Upon successful completion of this course, students will be able to:
Describe the workhorse methods that political scientists use to test their theories with data. See Readings and Exams & Grading for details on how this competency will be assessed.
Confidently analyze datasets using the
Rprogramming language, organizing this work so that it is transparent and reproducible. See Problem Sets for details on how this competency will be assessed.
Readings
Each week we will read a selection from our course textbook, Quantitative Social Science: An Introduction by Kosuke Imai (abbreviated QSS below). At the start of each class period, students will take a short reading quiz, in which they will be asked to summarize one or more of the key concepts from that week’s reading. These quizzes will be graded pass/fail, and there are 12 quizzes in total. To meet expectations, quiz responses must be accurate and clear enough that someone who hadn’t read the textbook could understand the response.
As you read each week’s assigned section, I strongly encourage you to follow along with the code examples by manually typing them into R and ensuring that everything works as expected. This practice will help you better understand how code works and prepare you for the problem sets.
Problem Sets
After class, I will assign an exercise from QSS as that week’s problem set, due before the following week’s class. Feel free to consult your classmates with questions about the problem sets, but I expect you to submit your answers individually. Resist the temptation to copy-paste code directly from your classmates or Claudes. You are much more likely to learn if you grapple with the coding yourself. Problem sets will be graded pass/fail, where a passing grade indicates that your solution is correct or contains only minor errors.
Exams & Grading
There will be two written exams: one midterm (scheduled for October 6) and one final exam (scheduled by the university during final exam period, December 8 from 3:30-6:30pm). Both exams will be graded out of 100 points. Exam content will be drawn from the readings and problem sets, and the final exam will be cumulative.
The final letter grade you earn for the semester will be determined based on the number of reading quizzes and problem sets you complete that meet expectations (each worth 5 points) and your performance on the exams (each worth 100 points). Consult the table below for the minimum requirements for each letter grade.
| Letter Grade | Points |
|---|---|
| A | 240+ |
| A- | 230-239 |
| B+ | 220-229 |
| B | 210-219 |
| B- | 200-209 |
| C+ | 185-199 |
| C | 170-184 |
| F | below 170 |
Office Hours and Email Policy
I will be available for students to drop in and chat every Thursday afternoon from 2-3pm. My office is Baldwin 304C. If you send me an email, please allow me 24 hours to respond. Like many professors, my inbox is pretty overloaded. Also, I have small children, so it’s my policy to not check email after 5pm or on weekends. You should feel free to seek assistance from the senior graduate students staffing the SPIA Methods Helpdesk. You can email them questions at spia-methods-help@uga.edu.
Course Outline
| Date | Module | Topic | Reading Quiz | Problem Set |
|---|---|---|---|---|
| Aug 18 | I. Introduction | Getting Started | QSS 1.5.2 | |
| Aug 25 | II. Causality | Experiments | QSS 2.1-2.4 | QSS 2.8.1 |
| Sep 1 | Observation | QSS 2.5-2.7 | QSS 2.8.3 | |
| Sep 8 | III. Measurement | Sampling | QSS 3.1-3.4 | QSS 3.9.2 |
| Sep 15 | Summary Statistics | QSS 3.5-3.8 | QSS 3.9.3 | |
| Sep 22 | IV. Prediction | Linear Models | QSS 4.1-4.2 | QSS 4.5.1 |
| Sep 29 | Regression and Causation | QSS 4.3-4.4 | QSS 4.5.2 | |
| Oct 6 | Midterm Exam | |||
| Oct 13 | V. Probability | Probability | QSS 6.1 | QSS 6.6.1 |
| Oct 20 | Conditional Probability | QSS 6.2 (skip 6.2.4) | – | |
| Oct 27 | Distributions | QSS 6.3-6.4 | QSS 6.6.3 | |
| Nov 3 | VI. Uncertainty | Estimation | QSS 7.1 | QSS 7.5.1 |
| Nov 10 | Hypothesis Testing | QSS 7.2 | QSS 7.5.2 | |
| Nov 17 | Model-Based Inference | QSS 7.3 | QSS 7.5.3 | |
| Dec 8 | Final Exam |