February, 2003
© 2000, 2001, 2003 Scott S. Emerson, M.D., Ph.D.
Session 1- Fixed Sample Design: 107
Case Study: Statistical Design Issues
Defining the method of analysis
Test for differences in binomial proportions
·Ease of interpretation
·1:1 correspondence with tests of odds ratio (for known baseline event rates)
·
No adjustment for covariates
Statistical information dictated by mean-variance relationship of Bernoulli random variable: p(1-p)