Statistical Analysis
Primary statistical analyses were performed in each
cohort independently on an intention-to-treat basis
with data from all participants who could be
assessed for the primary outcome. The analyses
compared the proportion of participants with peanut
allergy in the peanut-avoidance group with the
proportion with peanut allergy in the peanutconsumption
group at month 60 with the use of
a two-tailed chi-square test. Analyses of the data
from the two cohorts were independently powered.
In the cohort with negative results on the initial
skin-prick test, the power to detect a difference in
risk of 7 percentage points (9.0% in the avoidance
group vs. 2.0% in the consumption group) was