2.3 Theories of Group Sequential Tests
2.3.1 General Framework
In this section, we
define the test statistic to be monitored and specify its distributional
properties. This distributional theory is presented first in terms
of a general framework which is then applied to studies with normal,
binomial, and time-to-failure outcomes.
In the simplest situation,
if we consider a two-arm randomized clinical trial comparing a test
treatment with a control treatment, we can denote the treatment difference
by a parameter 
, which is also sometimes known as the effect metric. Depending on the stochastic model one chooses for the endpoint of interest, the ...
, which is also sometimes known as the effect metric. Depending on the stochastic model one chooses for the endpoint of interest, the ...Get Modern Approaches to Clinical Trials Using SAS: Classical, Adaptive, and Bayesian Methods now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
