Testing Secondary Hypotheses Following Sequential Clinical Trials

Sequential monitoring in a clinical trial poses difficulty in hypotheses testing on secondary endpoints after the trial is terminated. The conventional likelihood-based testing procedure that ignores the sequential monitoring inflates Type I error and undermines power. In this article, we show that the power of the conventional testing procedure can be substantially improved while the Type I error is controlled. The method is illustrated with a real clinical trial.

[1]  D. Zucker,et al.  Sequential monitoring of clinical trials: the role of information and Brownian motion. , 1993, Statistics in medicine.

[2]  A. Moss,et al.  Improved survival with an implanted defibrillator in patients with coronary disease at high risk for ventricular arrhythmia. Multicenter Automatic Defibrillator Implantation Trial Investigators. , 1996, The New England journal of medicine.

[3]  T. Fleming,et al.  Parameter estimation following group sequential hypothesis testing , 1990 .

[4]  Ross L. Prentice.  Discussion: On the role and analysis of secondary outcomes in clinical trials , 1997 .

[5]  S S Emerson,et al.  A computationally simpler algorithm for the UMVUE of a normal mean following a group sequential trial. , 1997, Biometrics.

[6]  David M. Reboussin,et al.  Information and information fractions for design and sequential monitoring of clinical trials , 1994 .

[7]  M. Relling,et al.  Human granulocyte colony-stimulating factor after induction chemotherapy in children with acute lymphoblastic leukemia. , 1997, The New England journal of medicine.

[8]  Christopher Jennison,et al.  Statistical Approaches to Interim Monitoring of Medical Trials: A Review and Commentary , 1990 .

[9]  M Tan,et al.  Clinical trial designs based on sequential conditional probability ratio tests and reverse stochastic curtailing. , 1998, Biometrics.

[10]  J. Whitehead.  Supplementary analysis at the conclusion of a sequential clinical trial. , 1986, Biometrics.

[11]  John Whitehead,et al.  On the bias of maximum likelihood estimation following a sequential test , 1986 .

[12]  R T O'Neill,et al.  Secondary endpoints cannot be validly analyzed if the primary endpoint does not demonstrate clear statistical significance. , 1997, Controlled clinical trials.

[13]  J. Whitehead,et al.  A FORTRAN program for the design and analysis of sequential clinical trials. , 1983, Computers and biomedical research, an international journal.

[14]  W. J. Hall,et al.  Minimum variance unbiased estimation of the drift of brownian motion with linear stopping boundaries , 1998 .

[15]  W. J. Hall.  The distribution of brownian motion on linear stopping boundaries , 1997 .

[16]  C. E. Davis,et al.  Secondary endpoints can be validly analyzed, even if the primary endpoint does not provide clear statistical significance. , 1997, Controlled clinical trials.

[17]  D. Siegmund.  Estimation following sequential tests , 1978 .

[18]  W. J. Hall,et al.  Unbiased estimation following a group sequential test , 1999 .

[19]  P. O'Brien,et al.  A multiple testing procedure for clinical trials. , 1979, Biometrics.

[20]  É. Bellissant,et al.  The triangular test to assess the efficacy of metoclopramide in gastroesophageal reflux , 1997, Clinical pharmacology and therapeutics.

[21]  S. Pocock.  Group sequential methods in the design and analysis of clinical trials , 1977 .