Generalized treatment effects for clinical trials

✍ Scribed by Walter W. Hauck; Terry Hyslop; Sharon Anderson

• Publisher: John Wiley and Sons
• Year: 2000
• Tongue: English
• Weight: 115 KB
• Volume: 19
• Category: Article
• ISSN: 0277-6715
• DOI: 10.1002/(sici)1097-0258(20000415)19:7<887::aid-sim388>3.0.co;2-l

✦ Synopsis

Practice in the analysis of clinical trials with continuously measured endpoints is to focus on the di!erence or percentage change in mean or median response. However, treatments may have e!ects on the distribution of responses other than on the average response. We sought an approach to such generalized treatment e!ects that: (i) targets a parameter that is easily understood by our clinical colleagues; and (ii) employs con"dence intervals as the basis for inference. We consider one such approach based on work in reliability theory, namely setting Pr[>'X] as the target parameter, and compare this approach to an earlier one due to O'Brien. The two approaches have similar properties when they both seek to reject the null hypothesis of no e!ect due to di!erent variances but di!er when the larger variance corresponds to the larger mean. In that case, our approach views that the larger variance attenuates the e!ect of the larger mean. Out suggested approach applies easily to positive control (clinical) equivalence trials.