IQMR 2026

Bayesian Inference for Qualitative Research (Modules 25, 29, 33)

Wednesday, June 24; Thursday, June 25; Friday, June 26

Eggers Hall, Room 060

Tasha Fairfield (European University Institute)

The way we intuitively approach qualitative research is similar to how we read detective novels. We consider different hypotheses to explain what happened—whether democratization 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 other salient knowledge we have. As we gather evidence and discover clues, we update our views about which hypothesis provides the best explanation—or we may introduce a new alternative that we think up along the way. Bayesianism provides a logically rigorous and intuitive framework that governs how we should revise our views about which hypothesis is more plausible, given our relevant prior knowledge and the evidence that we find 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. The principles we will cover in this module can be applied to single case studies (within-case analysis), comparative case studies (cross-case analysis), and multi-method research that draws on both qualitative evidence and quantitative data. Throughout, we will work with examples and exercises drawn from published social science research.

Book to Purchase: Tasha Fairfield and Andrew Charman. 2022. Social Inquiry and Bayesian Inference: Rethinking Qualitative Research. Cambridge University Press.

Participants may enter the module sequence after it has begun, but their doing so is discouraged. The material is highly cumulative.

Bayesian Inference for Qualitative Research I (M25, June 24)

8:45am - 10:15am – From Traditional Process Tracing to Bayesian Reasoning

This session will introduce the core ideas of Bayesian reasoning and draw contrasts with traditional process tracing and other qualitative case study methods. As time permits, we will move forward with an introduction to the basics of Bayesian probability, to be continued in the following session.

Required readings:

1:30pm - 3:00pm – Introduction to Bayesian Probability

We will review the notation of conditional probability and contrast the Bayesian notion of probability—our rational degree of belief given the information we possess—with the frequentist view of probability—relative frequency in an infinite series of repeated trials. As time allows, we will proceed to discuss rival hypotheses, what mutual exclusivity does and does not mean, and the importance of comparing alternative explanations, picking up where we leave off in the next session.

Required reading:

Suggested reading:

3:30pm - 5:00pm – Rival Hypotheses

Bayesian analysis—and essentially all inference—involves working with mutually exclusive (i.e., rival) hypotheses. Contrary to common perceptions, this requirement does not restrict the level of complexity or the number of variables that we can include in our explanations. Working in groups, participants will practice constructing a set of well-specified mutually exclusive hypotheses from two or three causal factors that might contribute to the outcome of interest. As time allows, we will continue on to the next steps in Bayesian reasoning.

Required reading:

Suggested reading:

Bayesian Inference for Qualitative Research II (M29, June 25)

8:45am - 10:15am – Assessing the Inferential Import of Evidence

One of the most important things that Bayesian reasoning can do for qualitative research is to help us make better judgments about how strongly our evidence favors one hypothesis relative to rivals. In this session, we will practice evaluating likelihood ratios, which determine the inferential import of the evidence. Here we need to “mentally inhabit the world” of each hypothesis and ask which one makes the evidence seem more expected. This is the key analytical step that tells us how to update our prior views about the relative plausibility of our hypotheses—we gain more confidence in whichever hypothesis makes the evidence more expected.

Required reading:

1:30pm - 3:00pm – Practicing Likelihood Ratio Reasoning

We will work on group exercises to give you practice evaluating how strongly qualitative evidence favors one explanation over a rival.

Required readings:

3:30pm - 5:00pm – Log-Odds Updating and Weight of Evidence

This session will introduce a simple linear version of Bayes’ rule that is easier to remember and easier to use, along with the weight of evidence, an intuitive concept promoted by Jack Good and Alan Turing that is closely related to the likelihood ratio. We will draw on real-world social science examples to practice evaluating the weight of evidence.

Required reading:

Suggested reading:

Bayesian Inference for Qualitative Research III (M33, June 26)

8:45am - 10:15am – Comparative Research and Case Selection

Methodological literature often treats cross-case (e.g., comparative) analysis and within-case analysis (e.g., process tracing) as distinct analytical endeavors that draw on different logics of inference. Within a Bayesian framework, however, there are no fundamental distinctions; all evidence contributes to inference in the same manner, whether we are studying a single case or multiple cases. In essence, each piece of evidence we obtain weighs in favor of one explanation over a rival to some degree, which we assess by asking which explanation makes that evidence more expected. Evidentiary weight then aggregates both within any given case, and across different cases that fall within the scope of the theories we are testing. We turn next to case selection, a topic of tremendous debate in the literature with much conflicting advice. Logical Bayesianism applies an information-theoretic approach, where the goal is to choose cases that will be highly informative for developing theory and/or for comparing rival hypotheses. We will discuss a number of practical guidelines for case selection that emerge from this information-theoretic approach.

Required readings:

Suggested reading:

10:45am - 12:15pm – Iterative Research

This session will give a Bayesian perspective on iterative research that involves going back and forth between theory refinement, data collection, and data analysis. Bayesianism provides a rigorous justification for many practices that are commonly employed in qualitative research but go against standard methodological prescriptions. As time allows, we will go on to discuss Bayesianism in relation to other methodological approaches.

Required reading:

1:30pm - 3:00pm – Wrapping Up

We will conclude the module by highlighting the relative advantages of Bayesianism and how it differs from other methodological approaches. The session will include a group exercise designed to elucidate key matters of Bayesian principle and practice, with an emphasis on clearing up some common misunderstandings.

Required reading: