estudio de caso segun yin tercera edicion

ANALIS DE ESTUDIO DE CASO

1. Robert K Yin (2003) Case study research: Design and Methods (3e)

2. Table of content 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 2 Introduction Designing the case study Conducting case study: Preparing for data collection Conducting case study: Collecting the evidence Analyzing case study evidence Reporting case studies

3. Introduction (1/2) Reasons for traditional prejudice against case studies Lack of rigor while performing research Confused case study teaching with case study research Concerns over generalizability They are too long, and results are massive, unreadable documents Data collection procedures are not routinized Case study purposes (not mutually exclusive) Explanatory Exploratory Descriptive The case study inquiry Copes with technically distinctive situations, with many more variables of interest than data points Relies on multiple sources of evidence Benefits from prior development of theoretical propositions A case study research shouldn’t be confused with ‘qualitative research’. Case studies are based on any mix of qualitative and quantitative evidence 4/14/2014 3 Prepared by Pavan Soni (IIM Bangalore)

4. Introduction (2/2) Purpose of case studies Explain the causal link Describe an intervention Illustrate certain topics within an evolution Explore situations where invention has no single output Meta-evaluation (study of evaluation study) Case studies are preferred strategy when: ‘How’ or ‘why’ questions are being posed, The investigator has little control over events When the focus is on contemporary phenomenon within some real- life context 4/14/2014 4 Prepared by Pavan Soni (IIM Bangalore)

5. Relevant solutions for different research strategies Strategy Forms of research quesiton Requires control of behavior events? Focuses on contemporary events? Experiments How. Why Yes Yes Survey Who. What. Where. How many. How much. No Yes Archival analysis Who. What. Where. How many. How much No Yes/ no History How. Why. No No Case study How. Why No Yes The essence of a case study, the central tendency among all types of case study, is that it tries to illuminate a decision or set of decisions; why they were taken; how there were implemented; and with what results. (Schramm, 1971) 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 (Yin, 1981) 4/14/2014 5 Prepared by Pavan Soni (IIM Bangalore)

6. Designing case studies Research design is a logical plan for getting from initial set of questions to be answered to set of conclusions Components A study’s question Its propositions (purpose in the case of exploratory case) Its unit of analysis The logic linking the data to propositions (through pattern- matching) Criteria for interpreting the findings Case studies are unsuitable to study the prevalence of a phenomenon, as done in statistical sampling Necessary conditions Construct validity Internal validity External validity Reliability Role of theory Essential to construct a preliminary theory (unlike in ethnography and grounded theory) Requires theoretical propositions (even for exploratory research) Helps generalize from case study to theory Analytical generalization and not statistical generalization 4/14/2014 6 Prepared by Pavan Soni (IIM Bangalore)

7. Design parameters Tests Definition Case study tactic Relevant phase of research Construct validity Correct operational measure for concepts Use multiple sources of evidence Establish chain of events Have key informants review draft case study report Data collection Data collection Composition Internal validity Establishing a non- spurious causal relationship (only for explanatory ) Do pattern matching Do explanation building Address rival explanation Use logic models Data collection Data collection Data collection Data collection External validity Establishing the domain for generalization Use theory in single case studies Use replication logic in multiple case studies Research design Research design Reliability Repeatability of operations of the case study Use case study protocol Develop case study database Data collection Data collection 4/14/2014 7 Prepared by Pavan Soni (IIM Bangalore)

8. Case study design (1/2) Rationale for single- case study design Represents a critical case in testing a well formulated theory Represents a extreme case or a unique circumstances Representative or a typical case (representative of experience of a large institution) Revelatory case (previously inaccessible to scientific community) Longitudinal case (how certain conditions change over time) Types of single-case design, based upon unit of analysis Embedded design (multiple units of analysis) Holistic design (single unit of analysis) Multiple- case study Replication, not sampling logic Literal replication (predicts similar results) Theoretical replication (predicts contrasting results but for predictable reasons) Replication is based on a rich theoretical framework. 4/14/2014 8 Prepared by Pavan Soni (IIM Bangalore)

9. Case study design (2/2) Generally multiple- case study preferred over single- case study, for these offer robust analytical conclusions (increases external validity) Multiple- case study design When external conditions are not thought to produce much variance in the phenomenon being studied, a smaller number of theoretical replication is needed. If you use a single-case design, prepare to make strong argument in justifying choices for the case. Heuristics for replication Settle for two or three replications when the rival theories are grossly different and issues at hand doesn’t demand an excessive degree of certainly If rivals are subtly different, and if high degree of certainly is desired, go for five to six replications. 4/14/2014 9 Prepared by Pavan Soni (IIM Bangalore)

10. Preparing for data collection Skills required for case study research Ask good questions Good listener Adaptive and flexible (not at the cost of rigor) Have a firm grasp on issues being studied Be unbiased by preconceived notions (being open to contrary) Training requirements Why the study is being done What evidence is being sought What variations can be anticipated What could constitute supportive or contrary evidence for any given proposition 4/14/2014 10 Prepared by Pavan Soni (IIM Bangalore)

11. Training session agenda Purpose of the case studies and research questions Review of case study nominations and of nomination procedures Schedule for doing case studies Preparation period Arrangement of site visit Conduct of site visit Follow- up activities Preparation of case study report Submission of draft report to site for review Review of case study protocol Discussion of relevant theoretical framework and literature Development or review of hypothetical logic model, if relevant In- depth discussion of protocol topics Outline of case study report Methodological remainders Fieldwork procedure Use of evidence Note taking and other field practices Other orienting topics Reading materials Sample case study reports Key substantive books and articles 4/14/2014 11 Prepared by Pavan Soni (IIM Bangalore)

12. Case study protocol Protocol is a standardized agenda for the investigator’s line of inquiry for a single case Overview of the case study project Background information Substantive issues to be investigated Relevant readings about the issue Introduction to the case study and purpose of protocol Case study questions, hypothesis, and propositions Theoretical framework for the case study (reproduces the logical model) Data collection procedures Name of the site to be visited, including contact persons Data collection plan Expected preparation prior to the site visits Case study questions Level 1: questions asked for specific interviewees Level 2: questions asked for the individual case Level 3: questions asked of the pattern of findings across multiple cases Level 4: questions asked for an entire study Level 5: normative questions about policy recommendation and conclusions Level 2 questions are more important then any, at the planning stage Outline of the case study report Importance of proper documentation 4/14/2014 12 Prepared by Pavan Soni (IIM Bangalore)

13. Data collection sources Individual behavior Individual attitudes Individual perceptions Archival records Other reporters behavior, attitudes, and perceptions How organizations work Why organizations work Personal policies Organizational outcomes About an individual About an organization From an individual From an organization Study conclusion If case study is an individual If case study is an organization Questions pertaining to unit of data are different from the unit of analysis of the entire case. 4/14/2014 13 Prepared by Pavan Soni (IIM Bangalore)

14. Pilot case study Why pilot case study Inquiry in the case is both broad and less focused Help refine data collection plans Pilot test is not a pretest Convenience, access and geography are main criteria for selecting pilot case Pilot case report must highlight the lessons learnt from research design and field procedures. 4/14/2014 14 Prepared by Pavan Soni (IIM Bangalore)

15. Conducting the case studies: Collecting the evidence Sources of data/ evidence Documents Archival records Interviews Direct observation Participant- observation Physical artifacts Principles of data collection Using multiple sources of evidence (triangulation to develop converging lines of inquiry. Strengthens construct validity) Creating a case study database Maintaining a chain of evidence 4/14/2014 15 Prepared by Pavan Soni (IIM Bangalore)

16. Sources of evidence- Documentation Forms Strengths Weaknesses Letters, memoranda, communications, agendas, announcements, minutes of meetings, written reports on events, administrative documents (proposals, progress reports, internal records), formal studies, newspaper clippings Stable- can be reviewed repeatedly Unobtrusive- not created as a result of the case study Exact- contains exact names, references, and details of an event Broad coverage- long span of time, many events, and many settings Retrievability- can be low Biased selectively, if collection is incomplete Reporting bias- reflects bias of authors Access- may be deliberately blocked 4/14/2014 16 Prepared by Pavan Soni (IIM Bangalore)

17. Sources of evidence- Archival records Forms Strengths Weaknesses Service records, organizational records, maps and charts, lists, survey data, and personal records Stable- can be reviewed repeatedly Unobtrusive- not created as a result of the case study Exact- contains exact names, references, and details of an event Broad coverage- long span of time, many events, and many settings Precise and quantitative Retrievability- can be low Biased selectively, if collection is incomplete Reporting bias- reflects bias of authors Access- may be deliberately blocked Accessibility due to privacy reasons 4/14/2014 17 Prepared by Pavan Soni (IIM Bangalore)

18. Sources of evidence- Interviews Forms Strengths Weaknesses Guided conversations, instead of structured queries. Important to 1) follow your own line of inquiry, as reflected by the case protocol; 2) to ask actual conversational questions in an unbiased manner. Open ended questions (espousing facts and opinions). Could even be a focused, short interview. Surveys. Targeted- focused directly on the case study topic Insightful- provides perceived causal inferences Bias due to poorly constructed questions Response bias Inaccuracies due to poor recall Reflexivity- interviewee gives what interviewer wants to hear 4/14/2014 18 Prepared by Pavan Soni (IIM Bangalore)

19. Sources of evidence- Direct observations Forms Strengths Weaknesses Behavior or environmental conditions worth observing at a site. Ranges from formal to casual data collection activities. Have more than a single observer. Reality- covers information in the real time Contextual- covers context of the event Time consuming Selectivity- unless broad coverage Reflexivity- event may proceed differently because it is being observed Cost- hours needed by human observation 4/14/2014 19 Prepared by Pavan Soni (IIM Bangalore)

20. Sources of evidence- Participant observation Forms Strengths Weaknesses You may assume a variety of roles within a case study situation and may actually participate in the events being studied. Usually used in anthropological studies Reality- covers information in the real time Contextual- covers context of the event Insightful into personal behaviors and motives Time consuming Selectivity- unless broad coverage Reflexivity- event may proceed differently because it is being observed Cost- hours needed by human observation Bias due to investigators’ manipulation of events 4/14/2014 20 Prepared by Pavan Soni (IIM Bangalore)

21. Sources of evidence- Physical artifacts Forms Strengths Weaknesses A technological device, a tool or instrument, a work of art, or some other physical evidence Insightful into cultural features Insightful into technical operations Selectivity Availability 4/14/2014 21 Prepared by Pavan Soni (IIM Bangalore)

22. Principles of data collection 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 22 Use multiple evidence Triangulation types (Patton, 1987) Of data sources (data triangulation) Among different evaluators (investigators triangulation) Of perspectives to the same data set (theory triangulation) Of methods (methodological triangulation) Create a case study database Organizing and documenting the data collected Two collections The data or evidence base The report of the investigator, whether in article, report or book format Uses notes, documents, tabular material, and narratives Maintain a chain of evidence Increases reliability External observer should be able to trace the steps in either direction Report should make sufficient citations to relevant portions Revel actual evidence and circumstances Consistency with protocol

23. Analyzing case study evidence 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 23 Steps of analysis Examining Categorizing Tabulating Creating a data display Testing Combining qualitative and quantitative evidence to address initial propositions Techniques for analysis Pattern matching Explanation building Time- series analysis Logic model Cross- case synthesis A good analysis should Attend to all the evidence (including the rival hypothesis) Must address all major rival interpretations Address most significant part of your case study Use your own prior expert knowledge

24. Generic strategies explained 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 24 Thinking about rival explanations Craft rivals The null hypothesis Threats to validity Investigator’s bias Real- life rivals Direct rival Commingled rival Implementation rival Rival theory Super rival Societal rival Relying on theoretical propositions Theoretical orientation guiding analysis Developing a case description Especially for descriptive case study

25. Specific analytical techniques (1/2) 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 25 Pattern matching Compares an empirically based pattern with a predicted one to strengthen internal validity Non- equivalent dependent variable as a pattern Rival explanations as patterns Simpler patterns Explanation building Relevant to explanatory case studies Iterative nature of explanation building Risk of drifting away from the original topic of interest

26. Specific analytical techniques (2/2) 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 26 Time- series analysis Only a single dependent and independent variable Detailed and precise tracing of events Trend matching with stated propositions, rival trends, or trends based upon artifacts Chronologies to investigate presumed causal events Interruption in time series as a potential causal relationship Logic models Stipulates a complex chain of events over time Staged in repeated cause- effect relationship Analysis can also entertain rival chains of events, and spurious external events Could be individual level or organizational level logic model Cross- case synthesis Pattern matching using word tables

27. Reporting case studies 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 27 Key elements Targeting case study reports Case study reports as part of the larger multi-method studies Illustrative structures for case study compositions Procedures to be followed in doing a case study report And, in conclusion, speculations on the characteristics of an exemplary case study Formats of case study report Classic single narrative, suitable for a book and not journal Multiple-case version with narratives, including cross-case analysis and results Presented in short question- answer formats, without narratives Entire report dedicated to cross- case analysis, descriptive or explanatory

28. Structures of reporting the case study 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 28 Type of structure Approach Explanatory Descriptive Exploratory Linear-analytic Issue/ problem  literature review  methods  findings  conclusion  implications X X X Comparative Repeats the same case-study two or more times comparing alternative descriptions or explanations X X X Chronological Present case study evidence in chronological order. Best practice is to draft the case study backwards. X X X Theory building Chapters follow theory building logic. X X Suspense Inverts the linear-analytic structure . Explaining the conclusions in chapters. X Unsequenced Sequence of chapters of no specific importance. X

29. Procedure in doing a case study report 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 29 When and how to start composing Bibliography and methodology section must be started Followed by descriptive data about the case being studied Case identities: real or anonymous Full disclosure is the most desirable option, helping reader link in previous research, and helps ease of review The review of the draft case study: The validating procedure Draft reviewed by peers, informants, and participants of the case

30. What makes an exemplary case study? 4/14/2014 Prepared by Pavan Soni (IIM Bangalore) 30 The case study must be significant The case study must be ‘complete ’ (setting of clear boundaries; collection of all the evidences; absence of certain artifactual conditions) Must consider alternative perspectives Must display sufficient evidence (presented neutrally with supporting and challenging data) Composed in an engaging manner (engagement, enticement, and seduction)