February, 2003
© 2000, 2001 Scott S. Emerson, M.D., Ph.D.
Session 3: 43
Schedule of Analyses
Example: Stopping rule chosen at first analysis (with estimates for later analyses)
One-sided test of a greater alternative:
Null : Theta <= 0      (size  = 0.025)
Alt  : Theta >= 0.5    (power = 0.975)
(Emerson & Fleming (1989) symmetric test)
STOPPING BOUNDARIES: Sample Mean scale
                             a      d
    Time 1 (N=  77.08) -0.0743 0.5744
    Time 2 (N= 154.16)  0.1211 0.3789
    Time 3 (N= 231.23)  0.2029 0.2971
    Time 4 (N= 308.31)  0.2500 0.2500