Bayesian Design of Noninferiority Clinical Trials with Co-primary Endpoints and Multiple Dose Comparison

We develop a Bayesian approach for the design of noninferiority clinical trials with co-primary endpoints and multiple dose comparison. The Bayesian approach has the potential of power increase and hence sample size reduction due to the incorporation of the historical data and the correlation structure among multiple co-primary endpoints while it still maintains the family-wise type I error control without additional multiplicity adjustment. In this chapter, we compare the Bayesian method to the conventional frequentist method with or without Bonferroni multiplicity adjustment resulting from the multiple dose comparison. The proposed method is also applied to the design of a clinical trial, in which the study drug at a low dose level and at a high dose level is compared with the active control in terms of the bivariate co-primary endpoints.

[1]  J. Ibrahim,et al.  Power prior distributions for regression models , 2000 .

[2]  Sue-Jane Wang,et al.  Multiple Testing of Noninferiority Hypotheses in Active Controlled Trials , 2004, Journal of biopharmaceutical statistics.

[3]  Kung-Jong Lui,et al.  Test Non-Inferiority and Sample Size Determination Based on the Odds Ratio Under a Cluster Randomized Trial with Noncompliance , 2010, Journal of biopharmaceutical statistics.

[4]  Iris Pigeot,et al.  A Comparison of Multiple Testing Procedures for the Gold Standard Non-Inferiority Trial , 2010, Journal of biopharmaceutical statistics.

[5]  Shunsuke Ono,et al.  Choice of control group in efficacy-showing clinical trials in Japan: does the ICH-E10 guideline change conventions? , 2002, International Journal of Pharmaceutical Medicine.

[6]  A. Tewari,et al.  A second phase III multicenter placebo controlled study of 2 dosages of modified release tamsulosin in patients with symptoms of benign prostatic hyperplasia. United States 93-01 Study Group. , 1998, The Journal of urology.

[7]  Yi Tsong,et al.  Simultaneous Test for Superiority and Noninferiority Hypotheses in Active-Controlled Clinical Trials , 2007, Journal of biopharmaceutical statistics.

[8]  Christy Chuang-Stein,et al.  Challenge of multiple co‐primary endpoints: a new approach , 2007, Statistics in medicine.

[9]  A. Dmitrienko,et al.  Gatekeeping procedures in dose–response clinical trials based on the Dunnett test , 2006, Pharmaceutical statistics.

[10]  Yi Liu,et al.  Partition testing in dose–response studies with multiple endpoints , 2007, Pharmaceutical statistics.

[11]  Anika Ashok,et al.  ICH Harmonised Tripartite Guideline , 2009 .

[12]  Scott Haughie,et al.  A placebo‐controlled study investigating the efficacy and safety of the phosphodiesterase type 5 inhibitor UK‐369,003 for the treatment of men with lower urinary tract symptoms associated with clinical benign prostatic hyperplasia , 2010, BJU international.

[13]  Joseph G Ibrahim,et al.  Bayesian Design of Noninferiority Trials for Medical Devices Using Historical Data , 2011, Biometrics.

[14]  Toshimitsu Hamasaki,et al.  A convenient formula for sample size calculations in clinical trials with multiple co‐primary continuous endpoints , 2012, Pharmaceutical statistics.

[15]  Tie-Hua Ng.  Issues of Simultaneous Tests for Noninferiority and Superiority , 2003, Journal of biopharmaceutical statistics.

[16]  James G. Scott,et al.  An exploration of aspects of Bayesian multiple testing , 2006 .

[17]  P. Westfall,et al.  Bayesian Multiple Testing for Two‐Sample Multivariate Endpoints , 2003, Biometrics.

[18]  Morris L. Eaton,et al.  On a multiple endpoints testing problem , 2007 .

[19]  Rebecca Finch,et al.  Multiple testing problems in pharmaceutical statistics. , 2014, Pharmaceutical statistics.

[20]  E. Laska,et al.  Testing Hypotheses about an Identified Treatment when there are Multiple Endpoints , 1992 .

[21]  Welch Bl.  THE GENERALIZATION OF ‘STUDENT'S’ PROBLEM WHEN SEVERAL DIFFERENT POPULATION VARLANCES ARE INVOLVED , 1947 .

[22]  Pilar Lim,et al.  A Dunnett-Bonferroni-based parallel gatekeeping procedure for dose-response clinical trials with multiple endpoints. , 2009, Pharmaceutical statistics.

[23]  R. Kay.  Statistical Principles for Clinical Trials , 1998, The Journal of international medical research.

[24]  Gary G Koch,et al.  Type I Error and Power in Noninferiority/Equivalence Trials with Correlated Multiple Endpoints: An Example from Vaccine Development Trials , 2004, Journal of biopharmaceutical statistics.