Statistics - explanations and formulas

Noninferiority Trials

reverse null/alternative hypotheses

  • Null hypothesis in traditional superiority trial: treatments are similar until proven otherwise
  • Null hypothesis in noninferiority trial:  standard treatment superior to new treatment unless proven otherwise (unless proven equivalent)
  • Predetermined equivalence range (): if results fall within this range, treatments considered equivalent
  • Several approaches to determining 
    • Clinical notion of minimally important effect (subjective)
    • Historical effect of active control in placebo trials
    • Regulatory requirements
    • Disease severity
    • At times, one treatment can even be a bit worse than the other tx so long as it falls within the equivalence range
  • Need different statistical analysis to determine superiority; may or may not be able to do so from same study depending on power