Considerations of power and sample size in rehabilitation research

Abstract

With the current emphasis on power and reproducibility, pressures are rising to increase sample sizes in rehabilitation research in order to reflect more accurate effect estimation and generalizable results. The conventional way of increasing power by enrolling more participants is less feasible in some fields of research. In particular, rehabilitation research faces considerable challenges in achieving this goal. We describe the specific challenges to increasing power by recruiting large sample sizes and obtaining large effects in rehabilitation research. Specifically, we discuss how variability within clinical populations, lack of common standards for selecting appropriate control groups; potentially reduced reliability of measurements of brain function in individuals recovering from a brain injury; biases involved in a priori effect size estimation, and higher budgetary and staffing requirements can influence considerations of sample and effect size in rehabilitation. We also describe solutions to these challenges, such as increased sampling per participant, improving experimental control, appropriate analyses, transparent result reporting and using innovative ways of harnessing the inherent variability of clinical populations. These solutions can improve statistical power and produce reliable and valid results even in the face of limited availability of large samples.

Keywords: MS; Neuroimaging; Power; Rehabilitation research; Sample size; Stroke; TBI.