Premium
Truncation of a Two Sample Sequential Wilcoxon Test
Author(s) -
Skovlund Eva
Publication year - 1991
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710330303
Subject(s) - truncation (statistics) , wilcoxon signed rank test , mathematics , range (aeronautics) , continuation , statistics , sample size determination , sequential analysis , sample (material) , boundary (topology) , mathematical analysis , computer science , mann–whitney u test , materials science , chemistry , chromatography , composite material , programming language
To reduce the number of patients needed in a clinical trial, a sequential plan is sometimes used. This paper deals with the truncation of a sequential two sample Wilcoxon test which was originally an open plan (S KOVLUND and W ALLØE , 1988). The truncated boundaries have been developed by stochastic simulation. These boundaries form a triangular continuation region. The simulated constants of the boundaries are presented in a table which may be used directly. Boundaries for truncation at 50, 100, 150 and 200 patients are developed. The chosen significance level may be 0.01, 0.025 or 0.05, and the power 0.95. To extend the applicability to other treatment differences than those tabulated, smooth curves are fitted to the simulated points. These make the test applicable to any treatment difference within the simulated range.