Interplay between design and analysis for behavioral intervention trials with community as the unit of randomization

Sylvan B. Green, Donald K. Corle, Mitchell H. Gail, Steven D. Mark, David Pee, Laurence S. Freedman, Barry I. Graubard, William R. Lynn

Research output: Contribution to journalArticlepeer-review

48 Scopus citations


This paper outlines an approach for the design and analysis of randomized controlled trials investigating community-based interventions for behavioral change aimed at health promotion. The approach is illustrated using the Community Intervention Trial for Smoking Cessation (COMMIT), conducted from 1988 to 1993, involving 11 pairs of communities in North America, matched on geographic location, size, and sociodemographic factors. The situation discussed is when assignment to intervention is done at the community level; for COMMIT, the very nature of the intervention required this. The number of communities is a key determinant of the statistical power of the trial. The use of matched pairs of communities can achieve a gain in statistical efficiency. Randomization is used to obtain an unbiased assessment of the intervention effect; randomization also provides the basis for the statistical analysis. Permutation tests (and corresponding test-based confidence intervals), using community as the unit of analysis, follow directly from the randomization distribution. Within this framework, individual-level covariates can be used for imputation of missing values and for adjusting analyses of intervention effect. Am J Epidemiol 1995; 142:587-93.

Original languageEnglish
Pages (from-to)587-593
Number of pages7
JournalAmerican Journal of Epidemiology
Issue number6
StatePublished - 15 Sep 1995
Externally publishedYes


  • Intervention studies
  • Matched-pair analysis
  • Random allocation
  • Randomized controlled trials
  • Smoking cessation
  • Statistics


Dive into the research topics of 'Interplay between design and analysis for behavioral intervention trials with community as the unit of randomization'. Together they form a unique fingerprint.

Cite this