published by Fariza Khalid

Want to create a visual like this?

Get Started
Conducting Research & Systematic Data Analysis
Dr. Fariza Khalid Faculty of Education UKM
Case Study
1. What is Case Study
5. Data Analysis 
6. Generalizability of Case Study
2. Features of Case Study
3. Sampling in Case Study
4. Types of Case Study
A bounded system (Smith, 1978)
What is Case?    
A boundary – enables you to limit the number of people involved who could be interviewed or a finite amount of time for observations. If there is no end, then the phenomenon is not bounded enough to qualify as a case (Merriam, 1998)
An integrated system (Stake, 1995)
A phenomenon of some sort occurring in a bounded context (Miles & Huberman, 1994)
What is Case Study?    
The case study is an approach that focuses on one or a small number of groups to investigate a contemporary phenomenon within its real context (Yin, 2009), for the purpose of gaining an in-depth understanding of the ‘events, relationships, experiences or processes occurring in that particular instance’ (Denscombe, 2010, p. 52).
When to conduct Case Study?    
Case study research is appropriate when the researcher wants to answer:
a descriptive question (e.g., what happened?) or
an explanatory question (e.g., how did something happen or why did it happen).

contemporary phenomenon
within a real context
multiple sources of evidences
to gain in-depth understanding
Features of Case Study
Focuses on a particular situation, event, program, or phenomenon.
Concentrate attention  on the way particular groups of people confront specific problems, taking a holistic of the situation.
The end product is a rich, thick description of the phenomenon
Case studies include as many variables as possible and portray their interaction often over a period of time.
Bring about the discovery of new meaning, extend the reader’s experience or confirm what is known
Previously unknown relationships and variables can be expected to emerge from case study leading to a rethinking of the phenomenon being studied. 

1.Single Case Study 2.Embedded Case Study 3.Multiple Case Study
A single-case study is an appropriate design under several circumstances.
Single Case Study
A rationale for a single-case study is when it represents the critical case in testing a well-formulated theory.
The single-case can then be used to determine whether a theory’s propositions are correct or whether some alternative set of explanations might be more relevant.
Involves more than one unit of analysis
This occurs when within a single case, attention is also given to a subunit of subunits
E.g. even though a case study might be about a single public program, the analysis might include outcomes from individual projects within the program
Embedded Case Study
Involve more than one case
Each case must be carefully selected so that it either (a) predicts similar results
Or (b) produces contrary results but for predictable reasons
Multiple Case Study
Multiple cases improve external validity
(Does the same thing happens in other settings?)

Multiple cases allows for greater understanding of contextual variations

Multiple case studies require cross-site analysis

Multiple Case Study
Documentation – letters, minutes of meetings, reports, articles etc
Interviews – open-ended, semi-structured, structured interviews
Archival records – service records, maps or charts, list of names, survey data etc
Resources of Data
Direct observation – observation of meetings, activities etc
Physical artifacts – tools, instruments, a work of art etc
Participant-observation – not merely a passive observer e.g being one of the staffs etc
Resources of Data
Determine the research questions 
Determining the questions is a critical step in case study research.
Case study research questions address who, what, how, and why.
Define the case under study
In this step the researcher defines the
 elements/variables under investigation/educational
 innovation being implemented

This step includes making a decision about whether or not to use theory development in selecting cases
Determine the role of theory development in case selection

Increasing the number of cases does not correspond to increased rigor.

Resist the temptation to add sub-cases unless it will strengthen understanding or theorising of the phenomenon under investigation.
Determine whether a single/multiple  case study

Case study research generally employs purposive or purposeful sampling.

Cases are selected because they are information rich, and the researcher can learn about the research problem.

Sample Selection 

Screening is used to determine if a potential participant has the necessary experience or knowledge of the phenomenon under investigation.
Sample Selection 
Sample Size 
1. There is no accurate answer!!! 2. What is needed is an ‘adequate’ number of participants., sites or activities to answer the question posed at the beginning of the study 3. Lincoln and Guba (1985) recommended sampling until a point of ‘saturation’ or redundancy is reached.
Data collection 
1. Case study researchers use the same data collection techniques as do other qualitative researchers.

2. The data collection techniques are selected to answer ‘how’ and ‘why’ questions.

3. Case study researchers triangulate their data through the use of multiple sources.
Data Analysis 
Meta matrix can be used to analyze complicated data specifically the one that involves multiple case/embeded case 

Meta matrix = Master charts with descriptive data from each site

As the matrix was so large, and used a large number of columns,  use symbols such as (+) and (-) to clarify the entries on display for each case.
Data Analysis 
Causal models/causal network can also be used 

Extends case study analysis

Presents possible cause-effect relations among variables
Can we generalize the findings from Case Study to the whole population?
Transferability replaces the concept of external validity for quantitative research (Lincoln and Guba, 1985). Transferability relates to the extent to which ‘the findings within one study can be applied to other studies’ (Shenton, 2004, p. 7).
The rich, in-depth data derived from multiple sources in the triangulation process may enhance the transferability of the findings (Linda, 2006).
However, the findings in case study research are impossible to statistically generalise beyond the specific research context (Bryman, 2004)
Analytical generalization = findings of case studies based on the theoretical propositions of a study can be projected onto a new situation (Yin, 2009)  
Fuzzy generalisation = generalisation is done based on prediction rather than on calculation (Bassey, 2001)
Yin (2009) states: ‘the basis of the generalisation is not the representativeness of the sample, but the fact that we discover a general principle about a phenomenon’ (p. 128).
A case study is an empirical inquiry that involves: - real-life context - boundaries between phenomenon and context - multiple sources of evidences - not meant for generalization
Thank You!