Adaptive Modifications of Hypotheses After an Interim Analysis

• Published in: Biometrical journal Vol. 43; no. 5; pp. 581 - 589
• Main Author: Hommel, Gerhard
• Format: Journal Article
• Language: English
• Published: Berlin WILEY-VCH Verlag Berlin GmbH 01.09.2001; WILEY‐VCH Verlag Berlin GmbH; Wiley-VCH
• Subjects: Adaptive designs; Closure test; Combination tests; Conditional error function; Control of multiple level; Exact sciences and technology; Experimental design; Interim analysis; Mathematics; Multivariate analysis; Nonparametric inference; p-values; Probability and statistics; Sciences and techniques of general use; Statistics; Two-stage designs; Design; Hypothesis test; Weighting; Error estimation; Optimal control; Error function; Error rate; Clinical trial; Planning; Mean value; Adaptive method; Multilevel system
• ISSN: 0323-3847; 1521-4036
• DOI: 10.1002/1521-4036(200109)43:5<581::AID-BIMJ581>3.0.CO;2-J

It is investigated how one can modify hypotheses in a trial after an interim analysis such that the type I error rate is controlled. If only a global statement is desired, a solution was given by Bauer (1989). For a general multiple testing problem, Kieser, Bauer and Lehmacher (1999) and Bauer and Kieser (1999) gave solutions, by means of which the initial set of hypotheses can be reduced after the interim analysis. The same techniques can be applied to obtain more flexible strategies, as changing weights of hypotheses, changing an a priori order, or even including new hypotheses. It is emphasized that the application of these methods requires very careful planning of a trial as well as a critical discussion of the scientific aims in order to avoid every manipulation.