Evaluating Single Case Research

To this point, we have primarily discussed the design, implementation, and analysis of single case studies conducted by you as a researcher or practitioner. Of course, researchers and practitioners must also analyze the studies conducted by others to contextualize their own studies and determine the extent to which evidence exists for a given practice in specific contexts (What works, for whom, and under what conditions?). Researchers evaluate rigor for several interrelated reasons, including to determine (1) to what extent an individual study was conducted in a manner to allow confidence in results, (2) to what extent a group of studies was conducted in a manner to allow confidence in overarching conclusions regarding outcomes, and (3) ways in which a body of research related to a specific independent or dependent variable should be expanded (e.g., What improvements in rigor are needed in future research? What questions have not been answered yet?). Regardless of whether you are assessing a single study or a group of related studies, it is critical that you assess rigor before you assess outcomes. This will allow you to determine whether changes in behavior are believable when compared against the degree of control for and detection of potential alternative explanations for an outcome across studies (i.e., whether you are confident that changes in behavior are due to experimental manipulations and only those manipulations).