February, 2003
© 2000, 2001, 2003 Scott S. Emerson, M.D., Ph.D.
Frequentist Methods 1: 86
Example
“Pocock” stopping rule with desired power
At each interim analysis, stop early if sample mean is indicated range
At the final analysis, the stopping must occur
 N      Harm        Equiv        Efficacy
 34   < -2.04   (-0.042,0.042)    > 2.04
 68   < -1.44   (-0.615,0.615)    > 1.44
101   < -1.18   (-0.869,0.869)    > 1.18
135   < -1.021  (-1.021,1.021)    > 1.021