Vrije Universiteit Amsterdam
-
Applying Quantitative Methods in Political Science
Graduate methods course
In this graduate course on applied quantitative methods, students will gain both theoretical knowledge and hands-on experience with quantitative research method. The course equips students with the tools to estimate empirically sound models that address substantive concerns in political science. While model estimation may be straightforward, the real challenge lies in developing models that yield meaningful insights into political phenomena. To achieve this, students will study the underlying principles of their chosen approach, develop research designs, and engage in data collection and analysis. Our focus will be on understanding how estimates are produced, what they signify, and determining which estimates can be trusted. The skills acquired in this course will also provide a solid foundation for students to apply in writing their MSc thesis.
-
Political Science Research: Philosophy and Design
Graduate methods course
This course is intended to introduce students to fundamental issues in the design of research in comparative political science and, therefore, to assist students in the development of their own research generally and more particularly in the preparation of their master dissertations. It focuses on the interplay of theory, hypotheses, empirical strategies, and data. The course is structured to deal with an interconnected set of issues facing researchers: the value of the comparative method in explaining political phenomena; the choice of substantively significant and tractable research topics; the development of concepts and their operationalisation; the choice of methods that match the research question; case selection and data collection; ethical issues in comparative political science.
-
Quantitative Research and Methods in Political Science
Undergraduate methods course
In an era in which quantitative data drives decision-making across sectors, this course equips students with the necessary tools to address questions in political science. The course aims to foster an understanding of how to apply quantitative techniques effectively. The objective of this course is to provide undergraduate students with the necessary statistical tools to make inferences about politics. The ability to quickly and accurately find, collect, manage, and analyse data is now a fundamental skill for quantitative social science researchers. We will cover fundamentals of probability theory, estimation, hypothesis testing and data visualization. These topics will be discussed with an eye on applications to research questions in all subfields of political science. Leaving this course, students will also be able to acquire, format, analyse, and visualize various types of data using the statistical programming language R. By bridging theoretical knowledge with practical skills in data analysis and causal reasoning, the goal is to cultivate a data literate generation of students capable of employing quantitative evidence to inform sound policy decisions.
-
Workshop in Democracy, Power and Inequality
Graduate comparative politics core seminar
This course aims to train students in doing political science and political economy themselves with a specific emphasis on democracy. This workshop surveys the literature on democracy to answer questions such as these: How is democracy conceptualised? What are the relevant distinctions among democracies? How can we measure democracy? What are the social, economic, cultural and political prerequisites of democracy? What effect does the political and economic performance have on the public support for democracy? Is democracy in decline today? These questions are approached by the selected literature both from the macro-perspective of institutions and context conditions as well as from the micro-perspective of the citizens and their understanding and evaluation of the way democracy works. At the same time, several of the selected texts deployed the methodological tools to approach these questions empirically.
ECPR Methods School
-
Bayesian Modelling
PhD methods course
This course aims at introducing the theoretical and applied principles of Bayesian statistics specifically geared toward students in social science. It will cover the differences between Bayesian and Frequentist approaches and the advantages of using the Bayesian approach for social scientists. Second, the course will cover the theoretical foundation of Bayesian statistics and introduce stochastic simulation methods for inference (Markov chain Monte Carlo). Third, it will focus on using Bayesian models in political science data analysis. The topics include linear models, logit/probit, poisson/negative binomial, hierarchical models, measurement models, as well as Bayesian model averaging. Examples are mainly drawn from political science, economics, and sociology.
-
Text as Data
PhD methods course
This course covers several methods for systematically extracting and analysing quantitative information from text for social scientific purposes. First, starting with information extraction, it discusses web scrapping techniques and how to obtain and process text data. Descriptive analysis of texts and dictionary methods will also be covered, followed by supervised and unsupervised machine learning techniques, scaling, topic models and embeddings. The course lays a theoretical foundation for text-as-data approach but mainly adopts an applied perspective, by introducing students to modern quantitative text analysis techniques, with the ultimate goal of providing the skills necessary to apply the methods in their own research.
Summer School in Social Science Methods, Lugano
-
Time Series Analysis for the Social Sciences
PhD methods course
Time series data lie at the core of political, economic, and social processes: public opinion shifts, government approval, macroeconomic indicators, media sentiment, policy changes, crises, and shocks are all phenomena that unfold over time. Yet most standard statistical tools assume independent observations and no temporal structure, assumptions that time-series data violate fundamentally. As a result, traditional regression approaches often produce misleading inferences, spurious findings, and incorrect conclusions, especially when series contain persistence, trends, unit roots, structural breaks, or long memory. This course offers a systematic introduction to time series analysis tailored to social scientists. Using real political and economic applications, participants learn how to diagnose temporal dependence, model dynamic relationships, test for stationarity, work with integrated processes, estimate autoregressive distributed lag (ADL) and error-correction models (ECMs), and understand concepts such as cointegration, equation balance and fractional integration. The course draws on examples from political science, economics, and public opinion research to highlight why theory must align with the data-generating process, and why many published time-series analyses fail due to mis-specification. The course is hands-on and emphasizes both conceptual understanding and applied modeling skills, with exercises designed to build reproducible workflows applicable to participants' own research.
IPSA Summer School
-
Bayesian Statistics
PhD methods course
This course introduces the theoretical and applied principles of Bayesian statistics. Although the Bayesian approach is highly useful, it is less commonly taught compared to the Frequentist paradigm. The Bayesian framework is particularly well-suited for the kinds of data political scientists encounter, as it provides a formal method for combining prior information with observed data, offers a flexible approach to model identification, and enables the fitting of complex, realistic models. The course begins by comparing Bayesian and Frequentist approaches, highlighting the advantages of Bayesian methods for social science research. It then covers the theoretical foundations of Bayesian statistics and introduces stochastic simulation methods for inference, such as Markov chain Monte Carlo. A significant focus will be on applying Bayesian models to political science data analysis, including standard models such as linear regression, logit/probit, Poisson/negative binomial, and hierarchical models, with additional topics like measurement models and Bayesian model averaging introduced in later sessions. The course aims to equip students with the ability to understand and apply Bayesian methods to research questions in quantitative political science, while also developing practical data analysis skills using the open-source statistical programming language R. Designed for students across social science disciplines, this advanced quantitative methods course is intended for those who have already received basic quantitative training.
European University Institute (2019)
-
Bayesian Statistics for Political Science
PhD & faculty methods course
This workshop aims at introducing the basic theoretical and applied principles of Bayesian statistics specifically geared toward researchers in political science. Despite the usefulness of the Bayesian approach, it is less taught among researchers of political science compared with the frequentist paradigm. The Bayesian framework is particularly useful for the type of data that political scientists encounter. It is a method for combining prior information with observed quantitative information; it offers a more general way to deal with issues of model identification, and it allows researchers to fit very realistic, sometimes complicated, models. Topics covered includes standard statistical models from a Bayesian perspective and advanced topics, such as models for multivariate outcomes and Bayesian change point analysis.