We live in an era of unprecedented data about political life, from voting records and public opinion surveys to campaign advertising and social media. This course is designed to make students active participants in that data-rich world. Using R throughout, students learn to load and wrangle data, produce effective visualizations, draw valid statistical inferences, and understand the fundamental limits of what data can tell us about causation. The emphasis is conceptual rather than narrowly mathematical. The goal is to understand why statistical tools work, not just how to execute them. The course culminates in a team research project in which students identify a question, collect data, and present an original analysis.
"I was surprised by how much I loved this class. Don't be afraid of getting it wrong, because Prof. Montgomery will kindly offer a correction and you will learn from that."Student course evaluation, Fall 2025
Throughout history, technological change has reshaped political power. Today is no different. Artificial intelligence, social media, satellite infrastructure, data centers, cryptocurrency, and search algorithms are transforming how power is exercised, contested, and projected within and across borders, with consequences we are only beginning to understand. This seminar examines both directions of that relationship. Students study how emerging technologies reshape political life in all its forms, from elections and governance to repression and armed conflict, and how governments and political actors in turn work to regulate, weaponize, and compete over them. Students engage with cutting-edge empirical research across all subfields of political science and develop an original research paper on a topic of their choosing. This course was featured in The Source.
Quantitative methodology never stands still. New models, estimators, and tools appear every year, and staying current over a research career takes more than learning the latest technique. It requires a fundamental understanding of how statistical inference works. Rather than surveying every method students might encounter, this course builds deep familiarity with the logic of inference across frequentist, Bayesian, and maximum likelihood traditions, then applies that foundation to the linear model and its many variants, the workhorse of the social sciences. Students who can reason clearly about how we learn from data, what assumptions a model requires, and what we can actually conclude from it will be equipped to engage with almost any quantitative approach they encounter in their research. The course is structured as a flipped class, with online lectures completed before each session and class time devoted to hands-on problem solving.
"I wish I had taken this course earlier in my career so that I could have developed my methodological skills sooner. I really appreciate Professor Montgomery's efforts to present complex material in an easy and accessible way."Student course evaluation, Fall 2025