Skip to main content
. 2014 May 6;8(2):e67–e72.

Table 1.

Design of a hypothetical trial comparing a new antibiotic with meropenem as a superiority trial or as a noninferiority trial, with a noninferiority margin of 2% for the outcome of clinical cure

Element of study Superiority trial Noninferiority trial
Null hypothesis (H0) The new antibiotic does not have a higher cure rate than meropenem The new antibiotic has a cure rate more than 2% lower than that of meropenem
Alternative hypothesis (H1) The new antibiotic does have a higher cure rate than meropenem The new antibiotic has a cure rate no more than 2% lower than that of meropenem
Difference between treatments required to disprove null hypothesis (H0) The lower bound of the 95% confidence interval must be greater than 0 The lower bound of the 95% confidence interval must not be lower than –2%
Factors that improve the likelihood of disproving null hypothesis (H0) Factors that result in greater differences between study groups Factors that result in smaller differences between study groups