POLS 642 — Intermediate Analysis of Political Data

Spring 2026 | Tu/Th 2:00-3:15pm | DuSable 464

Modified

August 25, 2024

ImportantKey Course Info
  • TOPIC:   This is an introduction to quantitative methods as used in political science research.
  • MODALITY:   This is an in-person course. We meet Tuesdays and Thursdays from 2-3:15 in DuSable 464.
  • ASSESSMENTS:   Major assessments consist of problem sets, a midterm exam, and a final project.
  • PREREQUISITES:   This course presumes successful completion of POLS 641 or an alternative introduction to statistics course that introduces students to the R programming language.
  • MATERIALS:   The main textbook used will be Nick Huntington Klein’s The Effect. Students in posession of Bailey’s Real Stats may use that as an alternative.

Instructor

Dr. Ches Thurber

  414 Zulauf Hall
  cthurber@niu.edu
  Office Hours: Tu/Th 12:30 - 1:30 pm
  Schedule an appointment

What is this course about?

This is the second course in the NIU Political Science Department’s quantitative methods sequence. It is now a required course for all Ph.D. students and strongly encouraged for all MA students. The course focuses on linear regression models with an emphasis on the concepts of probability and inference, the assumptions of linear regression estimation, and the application of linear models to research questions. Students should leave the course with the ability to engage with quantitative empirical research, to understand the core concepts and logic of causal inference, to employ basic OLS and logit models in their own research, and to further their statistical skills through either more advanced coursework or self-learning. In order to accomplish these goals, we will spend a significant amount of time learning statistical computer programming in R.

Mode of Delivery

This course will be conducted in person, twice a week. Students are expected to bring a laptop to class capable of running statistical software. Generally, we will focus on substantive topics on Tuesdays and programming on Thursdays.

Texts

The required textbook for the course is:

  • Nick Huntington-Klein. The Effect: An Introduction to Research Design and Causality Chapman and Hall, 2025.

A free online version is available here. If you would like a hard-copy version, you can order one here.

We will also frequently use the following alternative text for both required and supplementary readings:

  • Andrew Gelman, Jennifer Hill, and Aki Vekhari. Regression and Other Stories, Cambridge University Press, 2020.

A free (and legit) online PDF is available here.

If you previously purchased Bailey’s Real Stats, you are welcome to use that instead. The syllabus will include the pages from that text that align with the week’s topic.

Computer Programming in R

As part of this course, we will continue to use the statistical programming language R. It is assumed that students have developed a solid introduction to R in POLS 641 and we will build on that foundation. I will continue to teach R skills in class, we will do a lot of DataCamp exercises, and The Effect textbook includes code examples in R. But I will ask you to increasingly figure things out on your own. Part of the skillset being developed in this class is the ability to teach yourself going forward, both with regards to statistics as well as to programming (at least until AI makes programming unnecessary…)

Evaluation

Class attendance, preparation and participation (10%): The time we spend in class is for me the most important part of this course. As such, punctual attendance is mandatory. But more important than just being present at a desk is that you are actively engaged. I expect that you have done the readings and that you try to participate in discussion each and every class section. I also expect that you follow along with programming demonstrations and work with your classmates to complete in-class exercises.

Problem Sets and Data Camp(25%): You will have a number of problem sets to complete over the course of the semester. I encourage you to work in groups to complete the problem sets. However, I ask that the final work submitted be your own. This can be a little ambiguous, but to me means that 1) group work is conducted in a good-faith collaborative effort in which all participants are actively seeking to contribute; and 2) written work, including code, is produced by the individual student, not copied and pasted from other students’ work. I will also assign some lessons through the website Data Camp. I will check for completion and these will be worth less than the problem sets.

Midterm Exam (30%): There will be an in-class, closed-book midterm exam. Questions will be a mix of multiple choice and short answer.

Final Project (35%): You will produce a final project in written and presentational form. This project will involve an independent quantitative analysis of some type in which you develop a hypothesis or more, present relevant data and provide visualizations and basic descriptive measures, and evaluate your hypothesis with appropriate statistical tests including (but not limited to) linear regression. You will write-up a 10-page (or so) mini-paper and deliver a 10-minute conference-style presentation on the final day of class.

Grading Standards

As a graduate student, you are at the point in your professional development where it is your written work itself that matters (and how that work is received by a broader scholarly community) more than the grade arbitrarily assigned by a single cantankerous professor. Nevertheless, grades can serve as a helpful signaling device for your own self-assessment, for departmental funding decisions, and to admissions committees at PhD programs (for MA students planning to continue on…). The scheme below is taken from Prof. Kyle Beardsley in the political science department at Duke University with some modifications to adapt to our departmental norms and my own personal views. It may also be helpful to think about the grading distributionally. In the past, I have generally awarded between 1 and 3 straight As per graduate seminar. The modal grade has been an A-, with a few Bs and B+s.

  • A : Exceptional Performance. Outstanding work on all course-related tasks at a level that distinguishes the student from other members of the class. A comprehensive and incisive command of the issues, literature, and substantive information relevant to the course.The ability to master and integrate large amounts of factual material and abstract theories.

  • A- : Very Good Performance. Consistently strong work on all course-related tasks. A command of the issues, literature, and substantive information relevant to the course. Understands well and can integrate the relevant factual and theoretical material central to the course.

  • B+ : Good Performance. Solid work on all course-related tasks. A good grasp of the issues, literature, and substantive information relevant to the course. A very good command of factual and theoretical material, and some capacity to integrate the two.

  • B : Decent Performance. Generally consistent work on most course-related tasks. A general understanding of the issues, literature, and substantive information relevant to the course. An acceptable understanding of factual and theoretical material, but limited evidence of the capacity to integrate the two.

  • B- : Barely Satisfactory Performance. Mostly satisfactory work on course-related tasks, but with notable deficiencies. A general understanding of the issues, literature, and substantive information relevant to the course. Understands at a basic level the facts and theories related to the course, but with clear gaps, errors, or incomplete work. Grades lower than this represent unsatisfactory work.

Course Policies

  • Committed to your success: Beyond all else, I am committed to the success of every student in this class. I encourage everyone in the class to reach out to me if there is anything I can do in terms of the delivery of the course that would help you be more successful. I might not always be able to make it happen, but I will never discourage you from asking.

  • Names and Pronouns: It is my personal policy to allow graduate students to call me by my first name, “Ches.” This reflects the idea that I view you all as colleagues-in-training. I usually use the he/him/his pronouns to refer to myself, but am equally comfortable being referred to with they/them/their. Please let me know how you prefer to be addressed, both in name and pronoun, if it differs from what is in the college directory. I will make every effort to address you in the way you wish to be addressed. Please try and do the same for your fellow classmates, as well as for other faculty in the department.

  • Americans with Disabilities Act and Non-Discrimination Statement: If you need an accommodation for this class, please contact the Disability Resource Center as soon as possible. The DRC coordinates accommodations for students with disabilities. It is located on the 4th floor of the Health Services Building, and can be reached at 815-753-1303 or drc@niu.edu. Also, please contact me privately as soon as possible so we can discuss your accommodations. Please note that you will not be required to disclose your disability, only your accommodations. The sooner you let me know your needs, the sooner I can assist you in achieving your learning goals in this course.

  • Mental Health and Well-being: I understand that college students may experience a range of academic, social, and personal stressors, which can be overwhelming. You are not alone. Well-being at NIU offers resources, programs, and services. If you or someone you know need assistance with comprehensive or crisis mental health support, Counseling and Consultation Services (CCS) at 815-753-1206 is ready to help 24 hours a day, 7 days a week. Additionally, the National Suicide Prevention Lifeline can be reached at 988.

  • Academic Integrity: Good academic work must be based on honesty. The attempt of any student to present as his or her own work that which he or she has not produced is regarded by the faculty and administration as a serious offense. Students are considered to have cheated if they copy the work of another during an examination or turn in a paper or an assignment written, in whole or in part, by someone else. Students are guilty of plagiarism, intentional or not, if they copy material from books, magazines, or other sources without identifying and acknowledging those sources or if they paraphrase ideas from such sources without acknowledging them. Students guilty of, or assisting others in, either cheating or plagiarism on an assignment, quiz, or examination may receive a grade of F for the course involved and may be suspended or dismissed from the university.

    This is an issue I take seriously. Unfortuntely, it has increasingly become an issue in the graduate political science program. The creation of one’s own original work is the core of what a university education is all about. Falsely claiming credit for words or ideas that are not your own undermines that core. I will use software that tracks plagiarism as well as for similarities with classmates’ or even your own prior work. When work looks suspicious, I will often use additional measures to identify the original sources of plagiarized text. In this course, academic dishonesty in the forms of cheating on the midterm exam or plagiarism in th final project will always result in an F on the assignment and a formal misconduct report filed with the university. The recommendation I make in that report (e.g. failure from the course, suspension, expulsion from the university) will depend on the circumstance.

  • Artificial Intelligence: Generative artificial intelligence (AI) is almost certainly going to become a valuable tool for academic researchers and especially data analysts. Used well and in combination with strong critical thinking, writing, and programming skills, it may be able to help you be a better student and professional. The challenge, however, is that reliance on AI tools can short-circuit the learning process, preventing you from developing the skills and knowledge you need to be successful. Furthermore, AI is fraught with ethical, environmental, social, and intellectual property issues (see some thoughtful commentary by Prof. Andrew Heiss at Georgia State here).

For each assignment, I will provide specific instructions regarding the permissible and prohibited uses of AI tools. In general, the following principles will apply:

  1. The use of direct or paraphrased text from an AI source is explicitly prohibited in all cases. In cases where AI detectors identify a high probability of AI-generated content, the student will be invited to an oral examination of the content.

  2. Students may use AI tools to make grammatical/stylistic suggestions for text originally written by the student.

  3. Students may use AI as a research tool to identify sources and arguments within the literature. In such cases, students must ALWAYS identify, read, and cite the original source. Students will be held responsible for any incorrect information or hallucinated sources that come from AI tools.

  4. Students may use AI to help figure out how to implement a specific operation or statistical technique in R. Students MUST go through any code generated by AI line by line and understand what each line does. At any point, the instructor may ask a student to verbally explain the code used in a problem set or paper and to incorporate the quality of the answer into the grade for the assignment.

Class Schedule

Students are expected to complete readings in the Bailey text prior to Tuesday’s class. DataCamp lessons and R implementations from the Carilli book can be done before Thursday’s class.

Week 1: Introduction and Data Visualization

Tuesday Jan. 13

Thursday Jan. 15

  • Healy, Data Visualization, Chs. 1-3
  • Data Camp: “Introduction to the Tidyverse” or “Introduction to Data Visualization with ggplot2” (Due Friday Jan. 16 by 5PM)

Week 2: Describing Variables

Tuesday Jan. 20

  • The Effect: 3.1-3.4
  • Recommended: Data Camp “Foundations of Probability in R”

Thursday Jan. 22

  • The Effect: 3.5
  • Data Camp: “Hypothesis Testing in R” (DUE Friday Jan. 23 by 5PM)

Week 3: Describing Relationships

Tuesday Jan. 27

  • The Effect: 4.1-4.3
  • Optional Real Stats: Chs. 3, 14.1, 14.2

Thursday Jan. 29

  • The Effect: 4.4-4.7
  • Data Camp: “Simple Linear Regression” and “Predictions and Model Objects” (DUE Friday Jan. 30 by 5PM)

Week 4: Hypothesis Testing and Regressions

Tuesday Feb. 03

Thursday Feb. 05

  • The Effect: 13.2-13.2.3
  • Optional Real Stats: Ch. 6
  • Data Camp: “Assessing Model Fit” and “Parallel Slopes” (DUE Friday Feb. 06 by 5PM)

Week 5: Interactions and Logits

Tuesday Feb. 10

Thursday Feb. 12

  • The Effect: 13.2.6
  • Optional Real Stats: Ch. 12
  • Data Camp: “Interactions” and “Simple Logit Regression” (DUE Friday Feb. 13 by 5PM)

Week 6: Regression Assumptions and Diagnostics

Tuesday Feb. 17

Thursday Feb. 19

  • The Effect: 13.4-13.4.4
  • Optional Real Stats: Ch. 7
  • Data Camp: “Multiple Linear Regression” and “Multiple Logit Regression” (DUE Friday Feb. 20 by 5PM)

Week 7: Post-Estimation Analysis

Tuesday Feb. 24

  • Healy, Data Visualization, Ch. 6

Thursday Feb. 26

  • PROBLEM SET #1 (DUE Friday Feb. 27 by 5PM)

Week 8: Exam Week

Tuesday Mar. 03

  • Review Day

Thursday Mar. 05

  • Midterm Exam

Week 9: Spring Break

Week 10: Causality

Week 11: Experiments

  • Real Stats: Chapter 10
  • PROBLEM SET #2 (DUE Friday Mar. 27 by 5PM)

Week 12: Matching

Week 13: Time Series and Fixed Effects

  • The Effect Chapter 8
  • Optional: Real Stats: Chs. 8, 13, 15
  • PROBLEM SET #3 (DUE Friday Apr. 10 by 5PM)

Week 14: Event Studies and Diff-in-Diff

Week 15: Mixed Methods Research

  • Lieberman, “Nested Analysis”
  • Seawright and Gerring, “Case Selection Techniques in Case Study Research”

Week 16: Student Presentations

Tuesday Apr. 28

  • Student Presentations 1

Thursday Apr. 30

  • Student Presentations 2

Week 17: Finals Week

Tuesday May. 05

  • Student Presentations 3

Final Papers Due: Friday 5/8 at 5pm.