Rational Approaches for Choosing the True and False Positive Rates
S. D. Dubey CDER, FDA, Rockvill, MD 20857
In this paper, a Correct Decision Expectation Rate (CDER) Index is defined, developed, and described, which involves a function of the true and false positive rates with a sensible flexiblity factor. Similarly, a Trial Success Expectation Rate (TSER) Index is defined, developed, and described, which involves a valid and reliable measure of independent evidence, and the true and false positive rates. Various properties of these indices are derived and their consequences are discussed. Then a Trial Size Index is derived as a function of the CDER Index, the TSER Index, and the Expected Effect Size. Several insightful interactions among the CDER Index, the TSER Index, and the Trial Size Index are derived and their consequences are discussed. Finally, a wonderful world of interactive decision strategies involving true and false positive rates is produced with a view to assuring robust statistical evidence. The results of this paper are applicable under a spectrum of situations.