Co-Principal Investigator: Tipton, Elizabeth

Purpose: Great strides have been made in the last 15 years to generate methodological tools and benchmarks to support the design and planning of randomized controlled trials (RCTs) in K–12 education settings. However, the information needed to plan an RCT in the context of community colleges has not been well studied. The purpose of this project is to provide community college researchers with the same type of empirically based benchmarks, design parameters, and tools currently available for K–12 researchers planning and interpreting RCTs.

Project Activities: Part of planning an RCT involves having a sense of what a reasonable effect size might be for an intervention. This involves first determining what a meaningful and realistic change might be for important outcomes like retention, GPA, credits, and graduation. In this project, the research team will use existing data on student outcomes in the United States and effect estimates from 25 completed RCTs to build empirical benchmarks. The research team will use a similar approach to compile information about other important aspects of a power analysis, such as the predictive utility of covariates. In addition, the researchers will extend an existing tool, The Generalizer, which was developed by co-PI Tipton, to aid applied community college researchers in recruiting sites to be representative of a specified inference population. The research team will disseminate the grant findings by publishing MDRC working papers, peer-reviewed journal manuscripts, and giving presentations at conference, along with workshops on the newly developed community college version of The Generalizer.

Products and Publications

Somers, M. A., Weiss, M. J., & Hill, C. (2023). Design Parameters for Planning the Sample Size of Individual-Level Randomized Controlled Trials in Community Colleges. Evaluation Review, 47(4), 599–629.