Methods School

Learn how to use MAXQDA with your own data, make real progress during the course and use the 1:1 consultations for personalised feedback.

Understand how machine learning algorithms learn from data and apply these techniques to build supervised and unsupervised machine learning models that contribute to answering social science research questions.

Learn the logic of Bayesian inference and apply it to linear, generalised linear, multilevel and measurement models, from specifying priors and simulating posteriors to checking your models in quantitative social science research.

Learn the fundamentals, principles and practical tips for conducting high-quality case studies and process tracing. Using published studies as examples, you will work out the best research design and strategies for answering a given research question

Learn to explore, understand and communicate social science data through visualisation, using the grammar of graphics in R or Python to build effective figures, represent uncertainty and critically evaluate what makes a visualisation clear and honest

Build an understanding of the usefulness of a discourse analytic perspective and learn to apply discourse analytic tools to empirical materials, both your own and the example materials used in class.

This hands-on introduction to causal inference covers potential outcomes, randomised experiments, regression, causal graphs, matching and weighting, and sensitivity analysis.

Learn key aspects of Comparative Historical Analysis, including process tracing, path dependency, case selection, periodisation, and project design.

Learn how large language models work, explore how they can be used in social and political research, and develop a practical understanding of their strengths, limitations, and the challenges of evaluating and using them responsibly.

Gain practical skills in qualitative comparative analysis as you learn to design your research, analyse data, use specialised software, and effectively communicate your findings.

Learn how to analyse whole networks and personal networks, from how relational data are produced to how measures of position and composition enter a statistical model, with hands-on work in R.

Learn to work with spatial data in R, from building maps and geocoding addresses to measuring distances and detecting spatial clusters, and discover how geography can support causal inference in the social sciences.

Learn to specify, estimate and interpret latent variable models for survey item batteries, from exploratory and confirmatory factor analysis to binary, ordinal and explanatory item response theory, with practical exercises in R.

Learn to specify, estimate, interpret and report multilevel models in R for data nested in countries, schools or other groups, with a focus on the modelling decisions behind them, from centring and random slopes to cross-level interactions.

Learn ethnographic methods and writing, research design, quality and ethics, and gain practical experience in studying politics and power in a range of contexts.

Experience the key aspects of process tracing through practical, hands-on advice and techniques that can be applied in your own research project.

Introduce participants to interview research in political science and related disciplines, treating interviewing as both an art and a data-collection technique that requires training, practice, and reflexivity.

This class combines an introduction to classic text analysis and machine learning methods for social scientists with recent innovations for studying AI and large language models from a political science perspective.

Develop the tacit skills, as well as the formal skills and knowledge, you need to plan and carry out your own scholarly research project.

Build a solid foundation in statistical analysis with R. Learn Ordinary Least Squares regression and non-linear techniques, and their application in policy analysis and other contexts.

Learn to design and run effective surveys, from choosing a research design and sampling approach to developing questionnaires and conducting survey experiments, with practical guidance on addressing bias and assessing data quality.