We developed an interactive and menu-driven computer program to help investigators design and analyze phase II cancer clinical trials with a group sequential method, namely the sequential probability ratio test or the triangular test. Based on the values selected for the parameters of the trial, the
A class of truncated sequential nonparametric tests with constant boundaries: design and performance
โ Scribed by Sawasd Tantaratana
- Publisher
- Elsevier Science
- Year
- 1990
- Tongue
- English
- Weight
- 929 KB
- Volume
- 327
- Category
- Article
- ISSN
- 0016-0032
No coin nor oath required. For personal study only.
โฆ Synopsis
We consider the design and performance of a class of truncated sequential nonparametric tests with two constant thresholds for testing a shtft in the alternative. The design involves calculation of the thresholds and the truncation point. We propose to use the Asymptotic Relative EfJiciency (ARE) for this. First, the ARE of these tests with respect to the corresponding,fixed-sample-size (FSS) tests is obtained as a function of the ratio of the two thresholds, as well as the error probabilities. Given the desired error probabilities, the threshold ratio can be optimally chosen. Then, with this optimal choice and other associated constants, the thresholds can be calculated. Results show that the asymptotic performances of these tests are signtjkantly better than the corresponding FSS nonparametric tests. A sequential sign test is used as an example to demonstrate the design procedure and to show non-asymptotic performance, which a~qrees well with asymptotic results.
๐ SIMILAR VOLUMES