This is a methodological course on set-theoretic methods for the social sciences. While the spectrum of set-theoretic methods is broad, including techniques such as Mill’s methods or typological theory, this course primarily focuses on Qualitative Comparative Analysis (QCA). Invented by Charles Ragin [1987], this technique is still undergoing modifications, improvements, and ramifications with applications in fields as diverse as political science, public policy, international relations, sociology, business and management studies, or even musicology.

This course aims at enabling students to produce a publishable QCA of their own. In order to achieve this, the course provides both the formal set theoretical underpinnings of QCA and the technical and research practical skills necessary for performing a QCA. All applied parts of the course will be performed in the R software environment, using RStudio (Cloud). The course is structured as follows:

Week 1 of the course is dedicated to an introduction of the nuts and bolts of QCA as well as the R software environment. We start with some basics of formal logic and set theory. Then we introduce the notions of sets and how they are calibrated. After this, we move on to the concepts of causal complexity and of necessity and sufficiency, show how the latter denote subset relations, and then learn how such subset relations can be analyzed with so-called truth tables. We learn how to logically minimize truth tables and what the options for the treatment of so-called logical remainders are.

In Week 2, once participants master the current standard analysis practice, we discuss several extensions and improvements of QCA. Discussions in class will address from a set-theoretic point of view general methodological issues and advanced tools for solidifying and extending QCA. The topics covered include robustness tests, theory evaluation, case selection strategies for combining QCA with within-case process tracing, and the role of time and temporality in descriptive and causal inference.

Throughout the course, we will analyze fake and real data in the computer lab, using the R software environment and packages QCA and SetMethods. In addition to prepared datasets, which will be made available, participants are encouraged to bring their own raw data (even if this data is still tentative), which can be used for lab exercises and project work. Instructors and teaching assistants will be available for individual appointments with course participants to discuss research projects, questions regarding the design of a QCA study, and similar issues.