Cancer Clinical Trials: Current and Controversial Issues in Design and Analysis by Stephen L. George & Xiaofei Wang & Herbert Pang

Author:Stephen L. George & Xiaofei Wang & Herbert Pang
Language: eng
Format: epub
Publisher: CRC Press, Taylor & Francis Group
Published: 2016-04-23T04:00:00+00:00

7.2.4 p-Value Calculation

In a phase II trial, we conduct a statistical test to reject or accept the experimental therapy. If we reject or fail to reject the null hypothesis, we should be able to provide a p-value as a measure of how strong evidence the decision is against the null hypothesis. However, publications from phase II trials rarely report p-values to support their conclusions. In most of the publications, it is not even clear if the investigators decide to accept their therapies or not.

Using the stochastic ordering of UMVUE (7.3), Jung et al. [15] propose a p-value method for 2-stage phase II clinical trials. Noting that a p-value is defined as the probability of observing an extreme test statistic value toward the direction of H1 when H0 is true, they propose to calculate the probability of observing a UMVUE value larger than that obtained from the study under H0. Let denote the UMVUE of the RR observed from a two-stage phase II trial specified by (a1, b1, a, n1, n2). Given (M, S) = (m, s), the p-value = Pr{(M, S) ≥ (m, s)|p0} based on UMVUE can be calculated as

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.