Common RCT Designs

Parallel-Group Trial

  • Participants remain in one assigned group throughout the study.
  • Most common design.

Crossover Trial

  • Each participant receives both interventions in sequence.
  • Each participant serves as their own control.
  • Requires a washout period.
  • Appropriate for stable chronic conditions.
  • Avoid when:
    • Disease changes rapidly
    • Treatment has permanent effects
    • Carryover effects are likely

Factorial Trial

  • Tests ≥2 interventions simultaneously.
  • Example: drug A/placebo combined with drug B/placebo.

Cluster-Randomized Trial

  • Randomizes groups, eg, clinics or communities.
  • Useful when individual randomization would cause contamination.
  • Analysis must account for correlation among people within each cluster.