Centre for Behavioural Research and Program Evaluation A Case Study Primer in the Context of Complexity Barbara Riley, PhD CPHRI Research Methods Symposium Victoria, BC, May 4-8, 2009 The Centre for Behavioural Research and Program Evaluation is funded by the Canadian Cancer Society and located at the University of Waterloo.
Outline 1. Brief overview of perspectives table talk 2. Situations for case studies 3. Case study as a comprehensive research strategy 4. Research questions 5. Use of theory (including complexity) 6. Defining the case 7. Case study designs 8. Methods 9. Rigour
Perspectives on Case Studies Case study as: Weak research design Qualitative methodology Research strategy Data collection method Teaching technique Anecdotal report
Perspectives on Case Studies Case study as: Weak research design Qualitative methodology Research strategy Data collection method Teaching technique Anecdotal report 1. What description resonates with you, and why? 2. Why the diversity of perspectives?
Perspectives (2) Case study research can be difficult to conceptualize. It can use either qualitative or quantitative methods, can be prospective or retrospective, can have an inductive or deductive approach to theory, can focus on one case or many, can describe, explain or evaluate (Walshe et al, 2004: Case studies: a research strategy appropriate for palliative care? Palliative Medicine 18, 677-684, p.677)
Perspectives (3) A view from (enlightened) Harvard statisticians: many people feel that they can prepare a case study, and nearly all of us believe we can understand one. Since neither view is well founded, the case study receives a good deal of approbation it does not deserve. (Hoaglin et al, 1982: 134)
Perspectives (4) Donald T. Campbell: The core of the scientific method is not experimentation per se but rather the strategy connoted by the phrase plausible rival hypotheses. Findings are presented within extended networks of implications rather than context-free confirmation.
Situations for different research strategies Strategy Form of Research Question Control of behavioural events? Focuses on contemporary events? Experiment How, why? Yes Yes Survey Who, what, where, how many, how much? No Yes Arhival analysis Who, what, where, how many, how much? No Yes/No History How, why? No No Case study How, why? No Yes
The distinctive need for case studies arises out of the desire to understand complex social phenomena in complex systems. The case study retains the holistic and meaningful characteristics of real-life events (e.g., individual life cycles, organizational and managerial processes, neighbourhood change, etc) (Yin, 2003) In cutting up a system, the analytical method destroys what it seeks to understand (Cilliers, 1998, p.2)
Case study as a comprehensive research strategy Robert Yin, 1984, 1994, 2003 A case study is an empirical inquiry that investigates a contemporary phenomenon within its real-life context, especially when the boundaries between phenomenon and context are not clearly evident. The case study inquiry copes with the technically distinctive situation in which there will be many more variables of interest than data points, and as one result relies on multiple sources of evidence, with data needing to converge in a triangulating fashion, and as another result benefits from the prior development of theoretical propositions to guide data collection and analysis.
Components of research design 1. Study questions (substance & form) 2. Propositions, if any 3. Unit(s) of analysis, or case(s) 4. Logic linking data to propositions 5. Criteria for interpreting results
Research questions Descriptive: examine the interactions between advocacy campaigns and industry opponents Exploratory: explore the roles of government, researchers, and media Explanatory: identify characteristics of campaigns that are effective in changing health-damaging practices Freudenberg, Bradley, Serrano (2009) Public Health Campaigns to Change Industry Practices that Damage Health: An Analysis of 12 Case Studies. Health Education & Behavior, 36(2): 230-249.
Use of theory Two instances: 1) Develop propositions 2) Analytic generalization Propositions direct attention to something that should be examined within the scope of the study. Draw on relevant theories (e.g., individual, group, organizational, social)
Use of theory (2) Research question: How and why do organizations collaborate with one another? Proposition #1: organizations collaborate to derive mutual benefits (resource exchange theory) Proposition #2: organizations are more likely to collaborate when resources are limited (resource dependency theory)
Use of theory (3) Use of complexity theory: fosters an attitude of attention to emerging patterns, dynamism, and comprehensiveness while focusing attention on defined system properties; specifically, looking at patterns of relationships and interactions among the system s agents Anderson, Crabtree, Steele, McDaniel (2005) Case Study Research: The View from Complexity Science. Qual Health Res, 15: 669-685.
Defining the case Many options: person, incident, team, organization, program, decision, implementation process, organizational change Driven by the purpose of the study/research questions Issues to consider: Time period? Beginning and end points to the case?
Defining the case (2) Example #1: Context: community palliative care organization undertaking a change to its model of care that integrated a health promoting approach to end of life care Phenomenon: impact of the integration on organizational structures, processes, and outcomes Example #2: Context: shift in public health mandate to focus on prevention at a population level Phenomenon: dissemination of population-based prevention
Case study designs (Yin, 2003, p.40) Holistic (single unit of analysis) Single-case designs Multiple-case designs Embedded (multiple units of analysis)
Case study designs Holistic (single unit of analysis) Embedded (multiple units of analysis) Single-case designs Implementation of core public health programs in a single health authority Implementation of core public health programs in BC, with analyses at provincial, health authority and organizational levels Multiple-case designs Implementation of core programs in multiple health authorities Implementation of core public health programs in two provinces, with analyses at provincial, health authority and organizational levels
Case study designs: Single case studies 1. Critical case: tests a well-formulated theory 2. Extreme or unique case: unexpected results; rare situation 3. Representative or typical case: commonplace situation (typical neighbourhood) 4. Revelatory case: observe previously inaccessible phenomenon 5. Longitudinal case: same case over time
Case study designs: Multiple case studies Replication logic, not sampling logic. Case selected so that it a) predicts similar results (a literal replication) or b) predicts contrasting results but for predictable reasons (a theoretical replication) Example: Peter Szanton s (1981) book, Not Well Advised reviewed the experiences of numerous attempts by university and research groups to collaborate with city officials
Case study designs: Multiple case studies (2) 8 case studies: different university groups all failed to help cities 5 case studies: non-university groups also failed # case studies: university groups successfully helped business, engineering firms, and sectors other than government 3 case studies: groups able to help city government were concerned with implementation, not just new ideas Conclusion: city governments have peculiar needs in receiving advice Literal replication: within each of the four groups of case studies Theoretical replication: across the four groups
Methods a hallmark of case studies is multiple sources of evidence Quantitative methods are most appropriate to describe the extent of public health problems, and qualitative methods are most appropriate to provide understanding about complex, multi-faceted issues An increasing number of researchers now see the world with more pragmatic, ecumenical eyes (Miles & Huberman, 1994) Ways to combine: (Bryman, 1988) Triangulation Qualitative research facilitates quantitative research Quantitative research facilitates qualitative research Combined to produce a general picture
Rigour in case study research Yin, Lincoln & Guba, Baxter & Eyles Design tests Case study tactic Phase of research in which tactic occurs Construct validity / confirmability Internal validity / credibility External validity / transferability Reliability / dependability -Use of multiple sources of evidence -Establish chain of evidence -Have key informants review draft case study report -Do pattern matching -Do explanation building -Address rival explanations -Use logic models -Use theory in single-case studies -Use replication logic in multiple-case studies -Use case study protocol -Develop case study database Data collection Data collection Composition Data analysis Research design Data collection
Rigour in case study research (2) Greenhalgh, Russell, Swinglehurst: Narrative methods in quality improvement research. Qual Safety Health Care, 14: 443-449. Clear and focused research question? Use of a recognizable methodological approach? Rigorous and transparent application of approach? Reflexive awareness throughout the research process and in the research role? Identifiable unit of analysis (e.g., incident, organization, etc)? Competent and transparent attempt to analyze empirically collected data using a recognized theoretical framework?
Concluding remark from Robert Yin good case studies are difficult to do (2003; p.11)
Centre for Behavioural Research and Program Evaluation The Centre for Behavioural Research and Program Evaluation is funded by the Canadian Cancer Society. We are located at the University of Waterloo.