Small N designs for rehabilitation research

1
Small N designs for rehabilitation research

• Scott D. Barnett, PhD Allen W. Heinemann, PhD
  Alexander Libin, PhD Arthur C. Houts, PhD
  Julie Gassaway, MS, RN Sunil Sen-Gupta, PhD
  Aaron Resch, MS Daniel F. Brossart, PhD

2

• Study Aim
• Summarize strategies that rehabilitation
  researchers may consider for studying issues with
  expected small sample sizes.
• Relevance
• Underpowered studies, sample size requirements,
  and recruitment goals often plague rehabilitation
  research.
• Quasi-experimental and experimental small N
  designs are ideal methods for clinical research
  in which understanding and changing maladaptive
  patterns in behavior and functional status are
  primary goals.

3
Methods

• January 2010 State-of-the-Art conference
• Department of Veterans Affairs (VA)
  Rehabilitation Research and Development Service
  convened conference in Miami, Florida, to discuss
  current and future seminal issues pertinent to
  rehabilitation research both with and without VA
  services.

4
Results

• For single-case research
• Field has moved from visual analysis only to both
  visual and statistical analysis.
• Visual analysis of single-case data graphed over
  time is no longer sufficient.
• All single-case data should be analyzed using
  both visual and statistical methods.

5
Conclusions

• Small N studies (including pilot studies)
• Should be conducted more often.
• Are especially important in rehabilitation.
• Are specifically important during initial
  research development and the study of complex
  behavioral issues associated with co-occurring
  conditions.
• Administrators, grant reviewers, and journal
  editors should be educated on value of small N
  studies.