There have been situations, however, where the effect on the primary endpoint was not found to be statistically significant, but there did appear to be an effect on mortality or major morbidity. In the absence of a demonstrated treatment effect on the primary endpoint, secondary endpoints cannot be assessed statistically, but the suggestion of a favorable result on a major outcome such as mortality may be difficult to ignore.
One approach to avoid this situation would be to designate the mortality or morbidity endpoint as another primary endpoint, and apply one of the statistical methods of section IV with unequal splitting of the alpha. In this way, the endpoint can be validly tested, and should the effect be large, it will provide evidence of efficacy. Depending upon how alpha is allocated, the increase in sample size to maintain study power may only be modest.
MSB Price at posting:
$2.62 Sentiment: Sell Disclosure: Not Held
A personalised tool to help users track selected stocks. Delivering real-time notifications on price updates, announcements, and performance stats on each to help make informed investment decisions.
(20min delay)