Case study: collecting and analyzing

Data collection and the analysis of that data is likely to be the focus of your committee when considering whether or not your case study is a success. It’s important to collect sufficient amounts of the right types of data and analyze it according to the conventions of your discipline, or risk being required to start your case study over from scratch.

Data Types

There are three major data types: observation, documentation, and interviews. These can be further divided into participant and direct observation (for observation) and records, documents, and artifacts (for documentation). While it may be reasonable in terms of your particular project to focus on one type of data, it’s not advisable. One type of data may be sufficient, but it will nearly always lead to a stronger representation of your case study if you incorporate at least one other data type in your collection. This is not only due to the fact that multiple types of data strengthen your case study, but that multiple sources of data help to demonstrate that your conclusions are not outliers or anomalies.

Analyzing Data

Data alone is only information; it neither supports nor refutes a thesis or other ideas. In order for your data to be meaningful, it must be analyzed. There are multiple approaches to data analysis. All of them focus on identifying patterns in behavior or results which can then be used to support conclusions.

Expectations vs. Reality

Almost all researchers go into a case study with some expectations regarding the results. After all, they have formed a thesis and designed their data collection methods with the idea of supporting said thesis in mind. However, the very nature of a case study (or any serious research) means that it is very likely that at some point during their research, new ideas, patterns, and variables will present themselves. This is unavoidable when attempting to expand the knowledge base of one’s field by doing original research. It may not be expected, but it’s actually a positive outcome as it gives the researcher even more new information to work with. However, it may require the researcher to adjust their data collection and analysis plans significantly in order to include the new results.

Flexibility

As a result of this, it’s critical to have some sort of backup plan for how to collect and analyze unexpected results. You may even want to expand your research plan to include gathering information on these new variables as they appear.