Product Information:-

  • Journals
  • Books
  • Case Studies
  • Regional information
Request a service from our experts.
Visit the JDAL journal page.

How to... undertake case study research

Options:     Print Version - How to...  undertake case study research, part 4 Print view

Data analysis

If data collection for case studies is difficult, data analysis is no less so. The area is largely uncharted, in contrast to statistical analysis, where there are plenty of established techniques.

While there are software packages available (for example, The Ethnograph, ATLAS.ti, HyperRESEARCH, and NVivo), these do not provide analysable outputs. They may help with the organization of your material, but you need to come up with your own codes.

The analysis of qualitative data is covered in the guide, "How to ... analyse qualitative data", which may provide some useful hints.

Rowley (2002, p. 24) proposes the following principles for good case study analysis:

The analysis –

  • makes use of all the relevant evidence
  • considers all the major rival interpretations, and explores each of them in turn
  • should address the most significant aspect of the case study
  • should draw on the researcher's prior expert knowledge in the area of the case study, but in an unbiased and objective manner.

Various strategies can be used to code the data into different categories, from simple colour coding to content analysis (according to which data are grouped according to a number of variables), or grounded theory, where categories are established following the first phase of data collection and then used for the next phase of analysis.

The importance of having a general strategy

Yin (2009, location no. 2693) states that it is important to have a general analytic strategy, rather than hoping that patterns will emerge simply through studying and experimenting with the data.

He proposes four such strategies:

  1. Rely on the study's theoretical propositions. These should have informed the data collection, and during the analysis the researcher trawls through the evidence, looking for corroborative (or not) evidence. He or she then makes a judgement as to whether or not the initial propositions have been substantiated.
  2. Develop a descriptive framework for organizing the case study. This works well in an explanatory case study, set up to test certain propositions, however it may be less suitable for one that is descriptive or exploratory. An alternative strategy is therefore to consider how one will organize the report, and come up with a number of headings under which evidence will be grouped.
  3. Employ both qualitative and quantitative data. Some case studies employ only qualitative data. Some, however, use quantitative data, perhaps gained from surveys, or from existing statistics (for example crime rates, employees' salaries, student achievement). Providing that these data are central to the case study and to any propositions you are investigating, combining statistical and qualitative analysis will offer a strong strategy.
  4. Examine rival explanations. Your initial literature review may have examined rival hypotheses, which can then be checked against the evidence. This approach can be combined with any one of the other three.

Using analytical techniques

Yin (2009, location no. 2816) mentions five particular analytical techniques:

  1. Pattern matching. This involves comparing a predicted pattern with one revealed by the outcome of the case study. If there is a match, and the patterns coincide, then the initial proposition is confirmed, and the internal validity of the research is strengthened.
  2. Explanation building.
  3. Time-series analysis.
  4. Logic models.
  5. Cross-case synthesis. This method is applicable to any case research which employs at least two cases. Since more than one case will have been used for a reason, it is obviously necessary to compare findings across cases in order to reach valid conclusions. Each case is treated as a separate study, and the resulting data are compared. Tables are commonly used for this purpose, with a framework to suit the relevant data outcomes. Analysis of the tables then enables the researcher to draw conclusions across the data.

Of these, Yin (2009) describes pattern matching as "one of the most desirable" (location no. 2816), while cross-case analysis is obviously important in multiple case studies.

Other analytical techniques, such as content analysis, are described in "How to ... analyse qualitative data".


Once you have collected, analysed and formed conclusions from your data. The next step is, obviously, to share your findings with others by writing up your case study.

How you do this will vary according to your target audience. For example, if someone has commissioned you to write a report, the format will be different to that for an academic journal. The latter is covered in part 3 of the author guide, "How to ... write a case study".