A new paper from IES shows how research using single-case designs (SCDs) may contribute to our evidence base in education.

The field of education is increasingly committed to adopting evidence-based practices. Although randomized experimental designs provide strong evidence of the causal effects of interventions, they are not always feasible. For example, depending upon the research question, it may be difficult for researchers to find the number of children necessary for such research designs (e.g., to answer questions about impacts for children with low-incidence disabilities). A type of experimental design that is well suited for such low-incidence populations is the single-case design (SCD). These designs involve observations of a single case (e.g., a child or a classroom) over time in the absence and presence of an experimenter-controlled treatment manipulation to determine whether the outcome is systematically related to the treatment.

Research using SCD is often omitted from reviews of whether evidence-based practices work because there has not been a common metric to gauge effects as there is in group design research. To address this issue, the National Center for Education Research (NCER) and National Center for Special Education Research (NCSER) commissioned this paper by leading experts in methodology and SCD. Authors William Shadish, Larry Hedges, Robert Horner, and Samuel Odom contend that the best way to ensure that SCD research is accessible and informs policy decisions is to use good standardized effect size measures—indices that put results on a scale with the same meaning across studies—for statistical analyses. Included in this paper are the authors' recommendations for how SCD researchers can calculate and report on standardized between-case effect sizes, the way these effect sizes can be used for various audiences (including policymakers) to interpret findings, and how they can be used across studies to summarize the evidence base for education practices.

• Chapters 1 and 2 provide an overview of the paper and a detailed definition SCDs, their basic forms, and how they can be used to make causal inferences.
• Chapters 3 and 4 explain SCD research and the benefit of the use of effect sizes in general, the different types of standardized effect sizes (i.e., between-case and within-case), how they can be used in SCD research, and a suggested approach for reporting between-case effect sizes.
• Chapters 5 and 6 describe how to use between-case effect sizes for individual SCD studies, benefits that are likely to result from increased reporting of between-case effect sizes, and how these effect sizes can be used to identify evidence-based practices across studies.
• Chapter 7 provides recommendations for future directions and development of between-group effect sizes in SCD.