Every case study requires conception, design, preparation, execution, analysis, dissemination, and decision making, just as an experiment.A case study usually compares one situation with another: the results of using one method or tool with the results of using another, for example. To avoid bias and make sure that you are testing the relationship you hypothesize, you could organize your study in one of three ways:
- Sister projects means that you select two projects, each of which is typical for the organization and has similar values for the state variables that you have planned to measure. Then you apply the "old" treatment to one of the projects and the "new" to the other. By selecting projects that are as similar as possible, you are controlling as much as you can.
- Baseline means that the results of the "new" treatment is compared to a baseline computed from existing results of applications with the "old" treatment.
- Random selection means that a project is partitioned into parts, and that the parts then are randomly assigned to the different treatments.