BMET 23A25 - Introduction to R for Political Science and International Relations

This course provides a practical and conceptually grounded introduction to quantitative methods and data analysis using R, tailored to students in Political Science and International Relations. Building on the intuitive, step-by-step pedagogy of Data Analysis for Social Science (Llaudet & Imai), the course equips students with the skills to organise, explore, analyse, and interpret political data while developing a critical understanding of empirical research in comparative politics, international relations, and security studies.

Across twelve sessions (24 hours), students progress from fundamental data manipulation to core statistical inference and modelling, integrating conceptual insights from The Fundamentals of Political Science Research (Kellstedt & Whitten) and applied examples drawn from Political Analysis Using R (Monogan). Early sessions introduce the logic of quantitative political inquiry, the structure of data, and essential programming practices in R. Students learn how to import, clean, and reshape datasets; summarise and visualise political phenomena; and evaluate descriptive patterns in light of measurement and research-design concerns.

The central part of the course covers inferential tools widely used in political science, including hypothesis testing, linear regression, logistic regression, and count models. Each method is introduced through both its statistical rationale and hands-on applications to real political datasets, for example, public opinion surveys, democracy indicators, conflict event data, election results, and measures of governance. Throughout, students are encouraged to reflect on the strengths and limitations of quantitative evidence, the assumptions behind common models, and the challenges of working with complex or incomplete data.

The final part of the course focuses on reproducible analytical practice and basic programming principles in R, enabling students to structure scripts, write functions, and organise workflows effectively. The last two sessions are entirely devoted to a coding project in which each student designs and executes an empirical analysis using R. In week 11, students receive individual feedback on their code, modelling choices, and analytical strategy; in week 12, they present their scripts, logic, visualisations, and results to the class. This capstone exercise allows students to consolidate methodological skills, practice transparent research communication, and demonstrate their ability to conduct independent quantitative analysis.

By the end of the course, students will be able to perform standard statistical analyses in R, interpret model outputs, evaluate empirical claims in academic and policy debates, and produce clear, reproducible, and well-structured analytical code suitable for research in political science and international relations.

No prior programming experience is required for this course. However, it is recommended that you bring a laptop to class with some basic tools already installed, as they will be useful for hands-on activities. In particular, having R (version 3 or later) and RStudio installed locally is encouraged. In addition, it is important to ensure that access to a Google account is available, as Google Colab will be used for certain exercises. Institutional university accounts typically include access to Colab, but it should be verified that the account is active and that Google Colab can be opened and used without issues.

1°) Class participation 20%

Students are expected to actively participate in class discussions, contribute to collective reflections on readings, coding, and engage in Q&A sessions following lectures, presentations and exercises.

2°) Individual research code and design 80%

Students will produce an original R script and a short accompanying research design applying the tools, concepts, and methodological frameworks covered in class. The final submission must include:

A clearly formulated research question

A research design and hypothesis, explicitly justified through theoretical reasoning and relevant literature.

A methodological strategy, describing tools employed and explaining why these choices are appropriate for the research question.

An R script, fully reproducible, demonstrating correct data handling, modelling choices, visualisation, and interpretation of results.

A discussion of data sources, including their strengths, limitations, and relevance to cybersecurity politics.

A brief reflection on limitations, covering methodological constraints, issues of validity/reliability, and potential avenues for improvement.

The assessment will be based on the coherence between theory and empirical implementation, the quality and clarity of the R code, the robustness of the analytical choices, and the student’s ability to justify their approach both in writing and during the in-class consultations and presentations