Estimating of sample size
In accordance with FDA requirements for bioequivalence study, the
geometric mean ratio (GMR) is usually set at 95-105% under these
conditions (80% power, α=5%). The intra-subject variability (intra-CV)
for gefitinib is described to be 17-30%[7], and
the sample size calculation was carried out based on the smallest even
number of subjects. Additionally, considering the subject withdrawal of
10%, thus forty healthy male subjects were enrolled in the fasting or
fed group. Random order list was calculated by SAS statistical software
(version 9.4, SAS Institute, Cary, North Carolina), and all participants
were allocated into either a T or R group.