All Courses: This is a full list of courses we offer. Please see the “Upcoming Classes” tab for those included in SSPA 2024

Our courses are taught periodically in February and July. We also schedule courses for institutional clients, please get in touch with Prof. Ben Goldsmith to discuss.

Foundational Course

Foundations of Statistical Analysis in Political Science

The aim of this course is to provide students with an accessible introduction to the fundamentals of quantitative political science research. The course will be focused on understanding types of data; data visualization; bivariate statistical methods (t tests, chi-squared tests, correlation); and multivariate statistical methods (simple and multiple regression). [Instructor: Dr. Charles Miller]

Foundations of Programming in R for Political Analysis

This course provides hands-on experience for learning programming in R, a free and open-source language for statistical computing. Designed for newcomers without any prior programming background, the course covers foundational programming concepts, including basic R commands, operators, package utilization, functions, conditionals, and loops. Emphasis is then placed on the core areas of data science applied to political analysis, including data types such as categorical, continuous, discrete, and nominal; data structures like vectors, matrices, data frames, and lists; data wrangling techniques from data import/export to cleaning, addressing missing values, outliers, and transformations; exploratory data analysis focusing on measures of central tendency and descriptive statistics; and crafting data visualizations to create professional academic tables and figures for presenting distributions, crosstabulations, and correlations. Supplemental online resources, including in-depth mathematical materials, will be available to provide further elaboration on the discussed topics. [Instructor: Dr Thiago Nascimento da Silva]

Advanced Courses

Prerequisites: the foundational course or permission of instructor

Advanced Political Text Analysis

The course covers advanced methods for systematically extracting quantitative information from political text for social scientific purposes, building on the foundations from Political Text Analysis. The topics covered include: statistical scaling of texts to measure latent variables; topic models for estimating quantities from text using statistical techniques; classification methods for predicting document classes; clustering methods for text and word features; and ways to model and use word embedding to further improve model accuracy. [Instructor: Prof. Ken Benoit]

Bayesian Statistics I

The aim of this course is to provide an introduction to the Bayesian approach to statistical inference and estimation for applications in political science. Emphasis will be placed on the understanding the basic framework of Bayesian statistics and implementing and evaluating these models. Basic models will use basic R commands, while more complicated models will use a variety of commands from specific R model packages, as well as general modeling environments NIMBLE (a fast implementation of the BUGS model)and Stan, all run through R. Bayesian I will feature foundational 1 and 2 parameter models, linear regression, and applications to limited variable models (ordered and unordered logit/probit, count data, and multivariate regression). In addition to the scheduled lectures, background material on the models considered (e.g., basics of limited dependent variable models or basic usage of R) will be made available, while most mathematical content will be reserved for auxiliary recordings posted online. Prerequisites: Foundations of Statistical Analysis, or equivalent. [Instructor: Dr. Shawn Treier]

Bayesian Statistics II

The aim of this course is to cover several important advanced applications of the Bayesian approach to statistical inference and estimation in political science. Emphasis will be placed on the understanding the basics and implementation of these models. The statistical environment of R will be used, with specific models commands from R packages, as well as general modeling environments NIMBLE (a fast implementation of the BUGS model) and Stan. Bayesian 2 will feature hierarchical models (simple, linear regression, and more general specifications) and measurement models (factor analysis, IRT, ideal point estimation, LCA, SEMs). In addition to the scheduled lectures, background material on the models considered will be made available, while most mathematical content will be reserved for auxiliary recordings posted online. Prerequisites: Bayesian Statistics I or equivalent. [Instructor: Dr. Shawn Treier]

Introduction to Critical Discourse Analysis

The aim of this course is to introduce students to the foundations of Critical Discourse Analysis. The course will provide an overview of the foundations of CDA in critical and social theory, hermeneutics, social constructivism, and socio-linguistics before introducing students to the conceptual framework and analytical tools of CDA. [Instructor: Dr. April Biccum]

Introduction to Political Text Analysis

This course surveys methods for systematically extracting quantitative information from political text for social scientific purposes, starting with classical content analysis and dictionary-based methods, to classification methods, and state-of-the-art scaling methods and topic models for estimating quantities from text using statistical techniques. The course lays a theoretical foundation for text analysis but mainly takes a very practical and applied approach, so that students learn how to apply these methods in actual research. [Instructor: Prof. Ken Benoit]

Introduction to Social Network Analysis

The “network perspective” puts emphasis on social ties between actors, rather than individual characteristics, in understanding behaviour and outcomes. This course provides a practical introduction to the network perspective and social network analysis (SNA), with a focus on applications in social science, in particular political analysis. Students will learn about collecting and storing social network data, and will gain practical experience in visualising networks and constructing basic SNA metrics. There will also be an introduction to exponential random graph models (ERGM), which provide a statistical inferential framework for modelling interdependencies in social tie formation such homophily, reciprocity and transitivity. The course involves the use of R, with a focus on igraph for network visualisation and basic SNA, and statnet for ERGM. [Instructor: Professor Robert Ackland]

Longitudinal Data Analysis (Panel and Time Series data)

The aim of this course is to provide a practical, hands-on introduction to the analysis of longitudinal (repeated cross-sectional and panel) data for answering research and policy questions. The course will be focused on the following content areas: learning how longitudinal data differs from other forms of data; familiarising students with some common longitudinal datasets in the social sciences in Stata; understanding a number of statistical methods for analysing longitudinal data in Stata; and understanding how to interpret the results of these analyses. [Instructor: Dr. Feodor Snagovsky]

NOTE: This course will be taught in Stata. Students will require their own Stata licence.

Philosophy and Methods of Political Science

The course is based around Keith Dowding’s book of the same title. In the most general terms the course tries to provide a philosophically sound justification of both quantitative and qualitative research in terms of the different research questions they adopt. It considers the nature of explanation and the relationship of explanation to prediction, and the relationship of both to forecasting. It looks at the nature of theories about politics. It reconsiders the demand for causal inference and causal explanation in political science, and examines how description is an important part of explanation. It introduces the type/token distinction and the idea of the granularity of description and explanation. It covers the manner in which causation is approached by quantitative and qualitative methods, suggesting that both have compatible accounts and the difference between quantitative and qualitative work concerns the nature of the research questions they adopt. It examines the process-tracing account of qualitative research and asks in what ways case studies can test hypotheses drawn from theories. It considers the relationship between empirical generalizations and causal mechanisms and examines the use of models in political science. [Instructor: Prof. Keith Dowding]

Political Survey Design

Questionnaires are among the most common data collection methods that political researchers and other social scientists employ. This course introduces the principles of survey design and standard practices in the field. Practically oriented to initiate students to the design, administration, and analysis of surveys, it will cover the main aspects of survey methodology: key concepts and techniques; how design decisions affect empirical results; sampling and response maximization; questionnaire design gauging the impact of question wording; modes of data collection; and the basics of political survey data analysis. The course emphasizes learning and applying general insights as students work with concrete examples. [Instructor: Dr. Constanza Sanhueza]

Research Design and Causal Inference in Political Science

Causal inference is at the heart of many of the key questions in political science: - why do some nations democratize but not others? What are the causes of war and peace? How do we improve the representation of marginalized groups in political life? But causal inference is hard. In this course, we will examine the principles of good research design, with a particular focus on causal inference. We begin by examining what we mean by ‘causation’, ‘causal inference’ and ‘causal explanation’. We then move to examining a suite of techniques for answering causal questions: - experiments in their various forms, natural or quasi experimental methods such as instrumental variables, difference in differences and regression discontinuity designs, and methods for estimating causal quantities from observational data such as matching, sensitivity analysis and directed acyclic graphs (DAGs). [Instructor: Dr. Charles Miller]