Sequential decision strategy of the AML Cooperative Group studies.

Abstract

The ongoing 1985 studies are showing at present no clear advantage for either therapy. In the 1981 study, randomization was terminated by the sequential procedure after 161 randomizations. A test with the same alpha and beta but fixed sample size would have required at least 200 patients, 100 for each therapy. So in this case the use of the sequential procedure saved about 40 randomizations.