Dr Tasha Fairfield CON 6.02

This course is available on the MPhil/PhD in International Relations and MRes/PhD in International Development. This course is available with permission as an outside option to students on other programmes where regulations permit.

Students will be selected for DV560 based on a written statement of interest (max 150 words).  Priority will be given to students on the programs listed above, if demand exceeds places.

The way we intuitively approach qualitative case research is similar to how we read detective novels. We consider various different hypotheses to explain what occurred—whether the emergence of democracy in South Africa, or the death of Samuel Ratchett on the Orient Express—drawing on the literature we have read (e.g. theories of regime change, or other Agatha Christie mysteries) and any salient previous experiences we have had. As we gather evidence and discover new clues, we continually update our beliefs about which hypothesis provides the best explanation—or we may introduce a new alternative that occurs to us along the way.

Bayesianism provides a natural framework that is both logically rigorous and grounded in common sense, that governs how we should revise our degree of belief in the truth of a hypothesis—e.g., "mobilisation from below drove democratization in South Africa by altering economic elites’ regime preferences," (Wood 2001), or "a lone gangster sneaked onboard the train and killed Ratchett as revenge for being swindled"—given our relevant prior knowledge and new information that we obtain during our investigation. Bayesianism is enjoying a revival across many fields, and it offers a powerful tool for improving inference and analytic transparency in qualitative research.

This course introduces basic principles of Bayesian reasoning with the goal of helping us leverage our common-sense understandings of inference and hone our intuition when conducting causal analysis with qualitative evidence. We will examine the foundations of Bayesian probability as well as concrete applications to single case studies, comparative case studies, comparative historical analysis, and multi-methods research. Students will practice applying Bayesian reasoning to assess the strength and quality of inferences in published studies, drawing on exemplars of qualitative research from various fields of socio-political analysis including development studies, comparative politics, international relations, and policy analysis. Students will also apply Bayesian principles to various aspects of their own dissertation research in progress—e.g., generating or revising hypotheses, selecting cases, identifying weaknesses in salient background literature, and assessing the inferential weight of available evidence.

Upon completing the course, students will be equipped with a concrete set of Bayesian-inspired best practices to deploy in their own research, as well as widely-applicable analytic skills that will help them to better evaluate and critique socio-political analysis.

This course has no prerequisites. Students do not need any previous exposure to either Bayesian analysis or qualitative methods literature.

15 hours of lectures and 15 hours of seminars in the LT.

Students will attend DV460 lectures and seminars in LT.  Additional teaching and learning support in writing the final project will be agreed between the instructor and the student's PhD supervisor.  

Students will be expected to produce 1 exercise and 1 project in the LT.

Students will receive written and oral formative assessment on in-class exercises, which will ask them to explain key Bayesian concepts (e.g., the “weight of evidence”) in their own words and apply them to concrete examples (e.g. use Bayes’ rule to derive an inference from several pieces of evidence).

In addition, students will receive oral feedback on the first section of their final project, which will set up rival hypotheses to be compared in light of case evidence.

Methodological foundations:

Tasha Fairfield and Andrew Charman, “A Dialogue with the Data: The Bayesian Foundations of Iterative Research in Qualitative Social Science,” Perspectives on Politics 17(1:154-167), 2019; Andrew Bennett, “Disciplining Our Conjectures: Systematizing Process Tracing with Bayesian Analysis,” in Andrew Bennett and Jeffrey Checkel, eds, Process Tracing in the Social Sciences: From Metaphor to Analytic Tool, Cambridge University Press, 276–98, 2015; Tasha Fairfield and Andrew Charman, ”Explicit Bayesian Analysis for Process Tracing,” Political Analysis 25(363-380), 2017; Macartan Humphreys and Alan Jacobs, “Mixing Methods: A Bayesian Approach,” American Political Science Review 109(4):653-673, 2015; Timothy McKeown, “Case Studies and the Statistical Worldview,” International Organization 53(1):161-190, 1999.

Qualitative research exemplars:

Alan Jacobs, “How Do Ideas Matter? Mental Models and Attention in German Pension Politics,” Comparative Political Studies 42 (2) 2008; Tasha Fairfield and Candelaria Garay, “Redistribution under the Right in Latin America: Electoral Competition and Organized Actors in Policymaking,” Comparative Political Studies 50 (14) 1871-1906, 2017; Kenneth Schultz, "Fashoda Revisited" (Chapter 6) in Democracy and Coercive Diplomacy, Cambridge, 2001; Dan Slater, “Revolutions, Crackdowns, and Quiescence: Communal Elites and Democratic Mobilization in Southeast Asia,” American Journal of Sociology 115 (1) 203-254, 2009; Elisabeth Wood, “An Insurgent Path to Democracy: Popular Mobilization, Economic Interests, and Regime Transition in South Africa and El Salvador," Comparative Political Studies 34 (8) 862-888, 2001.

Project (100%, 5000 words) in the ST.

Students can choose from two options in consultation with the course instructor and the PhD supervisor, taking into account how far along they are in the research process:

(a) Conduct a full Bayesian scrutiny of a published work relevant to their dissertation topic, preferably one that analyses more than a single case.  Students will be asked to pay attention to some nuanced aspects of Bayesian inference, including logical dependence among multiple pieces of evidence, and they will provide quantified assessments of priors, weight of evidence, and their posterior degree of confidence in the author’s argument relative to rival explanations in light of the evidence. 

(b) Directly apply Bayesian reasoning to their own dissertation research in progress.  Students will devise at least two rival hypotheses to compare (preferably three), assess and justify priors in light of salient background literature they have read, and assess the weight of any available evidence they possess from their preliminary research and/or provide a Bayesian rationale for case selection.  Students will be asked to pay attention to some nuanced aspects of Bayesian inference, including logical dependence among multiple pieces of evidence, and they will provide quantified assessments of the weight of evidence and their degree of confidence in each hypothesis relative to the rivals in light of their background information and preliminary evidence.