Premium
Multistage Adaptive Test Procedures Based on Fisher's Product Criterion
Author(s) -
Wassmer Gernot
Publication year - 1999
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/(sici)1521-4036(199906)41:3<279::aid-bimj279>3.0.co;2-v
Subject(s) - early stopping , test (biology) , exact test , mathematics , statistics , computerized adaptive testing , interim , adaptive design , computer science , algorithm , machine learning , clinical trial , medicine , history , paleontology , archaeology , pathology , artificial neural network , biology , psychometrics
Tables for multistage test procedures that are based on a repeated significance test version of Fisher's combination test are presented. Bauer and Köhne (1994) and Bauer and Röhmel (1995) stressed the adaptive nature of the proposed procedure. The formers incorporated the stopping of the trial with the acceptance of H 0 and presented tables for the corresponding two‐stage and three‐stage test procedures. These methods are generalized for the application in clinical trials with more than two interim analyses. Different designing strategies are considered where stopping in favor of H 0 is possible. The proposed test procedures are compared with the classical non‐adaptive group sequential test designs.