Year: 2015
Type: book
Abstract: We apply insights from Bayesian analysis in the natural sciences to advance literature on causal inference in qualitative case research, building on and critiquing recent treatments of process tracing.Bayesian probability theory provides the uniquely consistent extension of deductive logic to situations where information is limited and uncertainty reigns.Whereas Bayesian statistical techniques have been successfully elaborated for quantitative research, applying Bayesian probability to qualitative research remains an open frontier.We provide best-practice guidelines for formal (quantified) Bayesian analysis, illustrated with the first systematic application to a case-study example.We envision important roles for formalization in pinpointing the locus of contention when scholars disagree on inferences, and in training intuition to follow Bayesian probability more systematically, thereby improving inference in qualitative research.However, quantifying qualitative data entails a substantial dose of arbitrariness that limits the utility of formally applying Bayesian analysis to complex case evidence.Formal analysis may also prove intractable beyond illustrative examples.Nevertheless, Bayesian probability is invaluable for elucidating methodological foundations and best practices for process tracing, which has contributed substantially to all realms of political science.Moreover, emphasizing the Bayesian underpinnings of qualitative case research can help to bridge between qualitative and quantitative methodological approaches to inference.
Authors: Tasha Fairfield, Andrew Charman
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
Keywords: causal inference, Bayesian probability
Open Access status: green
OpenAlex ID: W2408147699
