February, 2003
© 2000, 2001, 2003 Scott S. Emerson, M.D., Ph.D.
Session 1- Fixed Sample Design: 55
Decision Theoretic Approach
Decision Theoretic Issues: Asymmetry in treatment of null and alternative when using classical frequentist hypothesis testing
How to interpret a failure to reject the null?
·Would like to distinguish between
-inadequate precision (sample size)
-evidence against the alternative
Solution: Noncontiguous hypotheses
·Statistical design such that all but one hypothesis rejected with high confidence