ABSTRACT

In most randomized clinical trials, patient entry is sequential so that the results become available sequentially. Both medical ethics and the natural curiosity of investigators require an ongoing assessment of the accumulating data to see if a treatment difference is sufficient to stop the trial. This chapter outlines several of the more well-applied sequential testing procedures, including two- stage designs, the sequential probability ratio test, group-sequential tests, and adaptive sequential designs. From a logistical and cost-effectiveness point of view, it is natural to employ sequential testing approaches. Sequential analysis will be performed as "a method allowing hypothesis tests to be conducted on a number of occasions as data accumulate through the course of a trial. A trial monitored in this way is usually called a sequential trial". In fully sequential approaches, statistical tests are conducted after the collection of every observation. In group-sequential testing, tests are conducted after batches of data are observed.