Modification of Sample Size in Group Sequential Clinical Trials

Abstract

In group sequential clinical trials, sample size reestimation can be a complicated issue when it allows for change of sample size to be influenced by an observed sample path. Our simulation studies show that increasing sample size based on an interim estimate of the treatment difference can substantially inflate the probability of type I error in most practical situations. A new group sequential test procedure is developed by modifying the weights used in the traditional repeated significance two-sample mean test. The new test has the type I error probability preserved at the target level and can provide a substantial gain in power with the increase of sample size. Generalization of the new procedure is discussed.

Adaptive and nonadaptive group sequential tests

“…However, it would be difficult to prove the data revealed at interim analyses had played no part in the decision to re-design. We consider design modification according to Cui et al's (1999) , we define its efficiency index at to be…”

“…Fisher's (1932) method; this allows great flexibility in adapting the second stage to interim data but, to be valid, the method must be adopted at the outset. More recently, Cui et al (1999), L. D. Fisher (1998), Shen & Fisher (1999) and Müller & Schäfer (2001), among others, have proposed a variety of methods that preserve the type I error rate despite completely unplanned design changes. Although differing in appearance and derivation, these methods are closely related in that each preserves the conditional type I error probability whenever the design is modified; Jennison & Turnbull (2003) prove this must be the case for any unplanned re-design that preserves the overall type I error rate.…”

“…The publication of well over a hundred papers on adaptive designs in recent years indicates great enthusiasm for these methods, with potential uses well beyond the rescue of under-powered studies described by Cui et al (1999). In their illustrative examples, Lehmacher & Wassmer (1999) and Brannath, Posch & Bauer (2002) note the freedom given to investigators to re-design the remainder of a study at an interim stage.…”

“…2 Sample size adaptation to alter power 2.1 Adaptation preserving the type I error rate Cui et al (1999) cite instances in their experience at the U. S. Food and Drug Administration of researchers proposing an increase in sample size during the course of a group sequential trial based on the observed sample path. In one example, a Phase III study of a drug to prevent myocardial infarction in patients undergoing coronary artery bypass graft surgery was designed to have power 0.95 to detect a 50% reduction in incidence.…”

“…Such events motivated Cui et al (1999) (1999) suggest a single re-design point will usually suffice but the method easily extends to more.…”