Qualitative Causal Inference - Fundamentals and Applications (Modules 10, 14)

Wednesday, June 18; Friday, June 20

David Waldner (University of Virginia) and Ezequiel Gonzalez Ocantos (University of Oxford)

This module sequence introduces students to Qualitative Causal Inference (QCI), a hybrid model of inference that has important implications for how we think about and implement Process Tracing. In Part I, David Waldner outlines the fundamentals of QCI, contrasting it to two alternative models of inference: design-based causal inference, associated with the ‘credibility revolution’ in quantitative social science, and the detective model of causal inference championed by some Process Tracing methodologists. In these sessions students will become familiar with the distinct understanding of ‘causal mechanisms’ that underpins QCI. They will also learn to specify causal graphs to achieve unit-level causal inference, with attention to the mitigation of three potential sources of bias: (1) spuriousness and endogeneity via the construction of a ‘front-door path’ that indicates causal continuity between X and Y; (2) confounding variable bias by checking for the presence of a ‘back-door path’ that produces a non-causal association between X and Y; and (3) measurement error by checking for the presence of a ‘side-door path’ that complicates taking the pre-treatment value of the outcome variable as a proxy measure of the counterfactual (and inherently unobservable) value of the outcome under control. In Part II, Ezequiel Gonzalez-Ocantos examines QCI’s implications for Process Tracing. The sessions (a) offer practical modelling guidelines, with a focus on the construction of ‘front-door paths;’ (b) discuss how causal graphs orient and discipline data collection; (c) present techniques for dealing with missing data, a key challenge to meet the ‘front-door’ criterion; and (d) propose mitigation strategies for bias introduced by the ‘back and side-door paths.’

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

Qualitative Causal Inference: Fundamentals and Applications I (M10, June 18)

In Part I (Module 10) David Waldner outlines the fundamentals of QCI, contrasting it to two alternative models of inference: design-based causal inference, which is associated to the so-called ‘credibility revolution’ in quantitative social science, and the detective model of causal inference championed by some Process Tracing methodologists. In these sessions students will become familiar with the distinct understanding of ‘causal mechanisms’ that underpins this approach. They will also learn how to specify causal graphs in order to achieve unit-level causal inference, with attention to the mitigation of three potential sources of bias:

(1) spuriousness and endogeneity via the construction of a ‘front-door path’ that indicates causal continuity between X and Y; (2) confounding variable bias by checking for the presence of a “back-door path” that produces a non-causal association between X and Y; (3) measurement error by checking for the presence of a ‘side-door path’ that complicates taking the pre-treatment value of the outcome variable as a proxy measure of the counterfactual (and inherently unobservable) value of the outcome under control.

8:45am - 10:15am – Models of Inference

David Waldner

Required readings:

• David Waldner, Qualitative Causal Inference, chapters 1-2

1:30pm - 3:00pm – Foundations

David Waldner

Required readings:

• David Waldner, Qualitative Causal Inference, chapters 3-5

3:30pm - 5:00pm – Overview of Making Qualitative Causal Inferences

David Waldner

Required readings:

• David Waldner, Qualitative Causal Inference, chapters 6-7

Qualitative Causal Inference: Fundamentals and Applications II (M14, June 20)

In Part II (Module 14, Sessions 1-2) Ezequiel Gonzalez-Ocantos discusses the implications of QCI when using Process Tracing methods to achieve unit-level causal inference, i.e., explain outcomes in specific cases. QCI puts a premium on theory building prior to fieldwork, calling for the specification of causal graphs and their translation into event-history maps. These sessions will

(a) offer practical modelling guidelines, with a focus on the construction of ‘front-door paths;’ (b) discuss the various ways in which causal graphs should orient and discipline data collection, with examples of archive- and interview-based research; (c) present techniques for dealing with missing data, a key challenge when seeking to meet the ‘front-door’ criterion; (d) propose empirical and conceptual solutions to bias through the ‘back and side-door paths.’

In Part III (Module 14, Session 3), students will present their own causal graphs in small discussion groups, and receive feedback from other students and the instructors

8:45am - 10:15am – Nuts and Bolts of Making and Testing Models

Ezequiel Gonzalez-Ocantos

Required readings:

• Ezequiel Gonzalez-Ocantos, “Designing Qualitative Research Projects: Notes on Theory Building, Case Selection and Field Research,” in SAGE Handbook of Research Methods in Politics and International Relations

• Ezequiel González-Ocantos and Juan Masullo, “Aligning Interviewing with Process Tracing,” in Sociological Methods & Research

Suggested readings - examples used during the lecture:

• Mark Winward, “Intelligence Capacity and Mass Violence: Evidence from Indonesia,” in Comparative Political Studies

• Laura Gamboa, “Opposition at the Margins: Strategies Against the Erosion of Democracy in Colombia and Venezuela,” in Comparative Politics

• Ezequiel Gonzalez-Ocantos, “Persuade Them or Oust Them: Crafting Judicial Change and Transitional Justice in Argentina,” in Comparative Politics

1:30pm - 3:00pm – Challenges to Qualitative Causal Inference

Ezequiel Gonzalez-Ocantos

Required readings:

• Ezequiel Gonzalez-Ocantos and Jody LaPorte, “Process Tracing and the Problem of Missing Data,” in Sociological Methods & Research

• David Waldner, Qualitative Causal Inference, chapter 7.

3:30pm - 5:00pm – Causal Graphs Workshop

David Waldner and Ezequiel Gonzalez-Ocantos