February, 2003
© 2000, 2001, 2003 Scott S. Emerson, M.D., Ph.D.
Session 1- Fixed Sample Design: 115
S+SeqTrial
Designing the fixed sample study
Sample size and critical value
PROBABILITY MODEL and HYPOTHESES:
 Two arm study of binary response variable
 Theta is difference in probabilities (Treatment - Comparison)
 One-sided hypothesis test of a lesser alternative:
                                                                 
           Null hypothesis : Theta >=  0      (size  = 0.025)
    Alternative hypothesis : Theta <= -0.05   (power =  0.8)
   (Fixed sample test)
STOPPING BOUNDARIES: Sample Mean scale
                             a      d
    Time 1 (N= 2495.95) -0.035 -0.035