A new method of subgrouping in the crossover clinical trial using simulation techniques for performance evaluation.

摘要

We are interested in subgrouping subjects of a group for two-period crossover trials based on their response differences for two treatments. In this dissertation we compare two methods of subgrouping. We present the first method, based on a Threshold Level, a Critical Adjacent Factor (CAF), and a Majority Rule. The second method is given in Ghosh and Fairchild (2000). Three performance measures are used for our comparison. The first measure is the probability of identifying the correct number of subgroups. The second measure is the probability that a subject is correctly placed in a subgroup under the condition that the number of subgroups has been correctly identified. The third measure counts when subjects are subgrouped together who, in truth, belong to different subgroups. Extensive simulations are used for optimizing the new subgrouping method and for calculating the estimated numerical values of the performance measures, which are used to evaluate and compare the two subgrouping methods. We find that we were successful in improving the method of subgrouping upon that which is currently in the literature.