A 25‐year review of sequential methodology in clinical studies

Abstract

SUMMARYThis paper explores the theoretical developments and subsequent uptake of sequential methodology in clinical studies in the 25 years since Statistics in Medicine was launched. The review examines the contributions which have been made to all four phases into which clinical trials are traditionally classified and highlights major statistical advancements, together with assessing application of the techniques. The vast majority of work has been in the setting of phase III clinical trials and so emphasis will be placed here. Finally, comments are given indicating how the subject area may develop in the future.

Group Sequential and Adaptive Designs – A Review of Basic Concepts and Points of Discussion

“…Excellent review papers have already been published that focus mainly (but not always exclusively) on the technical side, e.g., by Proschan (1999), Wassmer (2000), Bauer, Brannath and Posch (2001), Bauer (2003), Jennison and Turnbull (2005) and Todd (2007). Textbooks include Wassmer (1999), Jennison and Turnbull (2000) and Chow and Chang (2006).…”

Sequential design with boundaries approach in pediatric intervention research reduces sample size

“…Several ways have been described to handle this necessity of parsimony and to maximize the probability of obtaining clear-cut results, which can be used to decide about the optimal treatment strategy in the clinical setting [8]. One method to reach statistically valid conclusions while including on average less subjects is called sequential design, in which the sample size that is attained at the end of the trial is unknown at the start [9]. With fixed values for type I (a) and II (b) errors and the expected (or minimal) clinically relevant effect size, stopping rules are defined, based on the accumulated information.…”

“…(2) boundaries designs, which include the sequential probability ratio test (SPRT) [11], the triangular test [10], and repeated significance testing (RST) [12]; and (3) adaptive designs [9]. However, there appears to be no consensus about the classification of various types of sequential designs among scientists.…”

Recent developments in clinical trial designs for HIV vaccine research

“…A relevant impetus for rethinking HIV vaccine trial designs today is the demand to accelerate the clinical development of [25][26][27] Multi-arm trials have more than 2 arms, which can increase efficiency in terms of sample size, for example by comparing more than one active vaccine arm to a common control arm or by using factorial designs (Fig. 1).…”