| Summary: | 碩士 === 國立成功大學 === 統計學系 === 88 === Adaptive clinical trials play a pivotal role because they
allow for information accumulated early in the trial to
influence the allocation of treatment of later enrolled patients. Few adaptive clinical trials have been reported in the literature. The purpose of this article is to calculate the influence of different data order, included the order of treatment and outcomes, for deciding which one of two treatments is better and reducing the number of patient
subjects with the poor treatment. A comparison of five allocation rules given in the article with empirical powers, empirical sizes and the expected number of patients with the better treatment by computer simulations. Simulation results show that patients allocated adaptive
design in the second stage using the response outcomes of patients allocated completely randomized design in the first stage gives substantial improvement over other allocation rules. Furthermore, the sequential likelihood ratio sampling procedure is considered to reduce the number of patients allocated adaptive design for ethical reason.
|
|---|
