Case studies usually explore a complex single instance (of an individual, organisation, project, event) taken as a whole in its context - providing a comprehensive description and analysis of that instance using multiple sources of data.
Case studies are useful when there is a concern to understand how and why questions and the process or project being investigated needs to be explored as a meaningful whole within its real life setting. In evaluation, explanatory case studies are useful to explain the presumed causal links in real-life interventions that are too complex for survey or experimental designs. Case studies can also be used in a variety of other ways, including exploratory case studies to illuminate aspects of a situation or setting about which little is already known.
The need to understand context usually means there are many factors and aspects of a situation that need to be taken into account even while there may not be comprehensive data on all of them. In this situation triangulation of evidence is crucial. It is important to build up a chain of evidence supporting the claims made about the case, but also to test rival explanations for the characteristics and events described. In turn, for evaluation as much as for other case studies, this means it is important to develop clear theories about how change is brought about by an intervention (its theory of change). Making clear the assumptions about how changes happen also supports the development of clear evaluation questions to guide data collection and analysis.
A definition from Yin (2009) suggests that a case study is an empirical enquiry which:
- investigates a contemporary phenomenon in depth and within its real life context, especially when the boundaries between the phenomenon and context are not clearly evident;
- copes with the technically distinctive situation in which there will be many more variables of interest than data points;
- and, as a result, relies on multiple sources of evidence with data needing to converge in a triangulating fashion.
Case studies are often misunderstood as a purely qualitative, descriptive method and criticised as being unrepresentative when compared with survey and other quantitative methods. However, the case study is not a sample and the aim of a case study is not to enumerate the frequencies of one or two key variables in a way that can be seen as representative of a larger population to which the findings can be generalised. Rather, case studies, like experiments, follow a logic of replication where it is the theory (of how change happens) which is tested and generalised to new cases in empirical studies. In technical terms the case study uses‘analytical generalisation rather than the‘statistical generalisation of randomised assignment to treatments.
On the other hand, many descriptive accounts are often wrongly called case studies when none of the procedures that make up a rigorous case study approach have been applied (teaching case studies are also usually a different entity to the rigorous case studies used in research or evaluation. Case studies, like any other method, can be done rigorously or less so, depending on how carefully and thoughtfully they are designed and conducted. In many ways they are more difficult than other methods to do well, since they attempt to triangulate and combine a range of different types of data and a range of approaches to gather that data.
Comparing or contrasting a range of case studies can increase the confidence that the factors and processes being demonstrated through the case are more widely applicable.
Recently, a powerful new approach for systematic case comparison has been developed, called Qualitative Comparative Analysis. This approach supports research and analysis into complex cases in a way that preserves their integrity as wholes embedded in their own contexts, but which also allows comparison and generalisation across many examples to draw out key combinations of factors that seem to make a difference.
Video Introduction to Case Studies
Caption: This is part one of three in a series of video introductions to evaluation case studies by Graham Gibbs of Huddersfield University (19 minutes). The remaining two parts are available on YouTube. The videos give a general introduction to the basics of the case study as a distinctive method, explain different types of case studies and provide examples. Credit: Graham Gibbs. License: Attribution-NonCommercial-ShareAlike.
More Introductory Information
Book: Case Study Research: Design and Methods (219 pages)
Fourth Edition, California: SAGE. Robert Yin 2009
The definitive guide to conducting rigorous case studies, outlining the distinctive advantages of the case study approach in comparison with other methods. Includes a clear step-by-step treatment of the selection of cases, different types of case study and case study design, gathering evidence and data, analysis and reporting, and criteria for quality, with a range of practical examples and links to illustrative reference materials. It does not focus only on the use of the case study methods in evaluation, but is valuable for clearly outlining the components of a rigorous case study approach.
A clear overview introduction to the distinctive character of case studies, the range of types of case study in evaluation with short illustrative examples of these types drawn from World Bank development assistance programmes. The paper usefully outlines the rationale for selection of different types of case study for evaluation, depending on the evaluation questions that need to be answered.
More resources on Evaluation Case Studies can be found in the Mesh Evaluation Case Studies resources category.To see how this resource fits in with the rest of Mesh's evaluation resources, and to learn how to navigate them, visit the Mesh evaluation page.
This resource was developed by Robin Vincent as part of supporting the Wellcome Trust linked community of practice on evaluation of public and community engagement and was originally hosted on the eMOPs website.
This work, unless stated otherwise, is licensed under a Creative Commons Attribution 4.0 International License