February, 2003
© 2000, 2001, 2003 Scott S. Emerson, M.D., Ph.D.
Session 1- Fixed Sample Design: 113
Case Study: Statistical Design Issues
Determining the sample size (cont.)
Fixed sample test (no interim analyses):
·d = (z1-a + zb) for size a, power b
Two sample test of binomial proportions
·D = (pT1 - pC1) - (pT0 - pC0)
·V = pT1 (1 - pT1) + pC1 (1 - pC1)  under H1
·n = sample size per arm